Cover Image

Which Sparse Autoencoder Features Are Real? Model-X Knockoffs for False Discovery Rate Control

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Enkhbayar, Tsogt-Ochir
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A New Way: Kronecker-Factored Approximate Curvature Deep Hedging and its Benefits
by: Enkhbayar, Tsogt-Ochir
Published: (2024)

Learning from Negative Examples: Why Warning-Framed Training Data Teaches What It Warns Against
by: Enkhbayar, Tsogt-Ochir
Published: (2025)

Atomic Literary Styling: Mechanistic Manipulation of Prose Generation in Neural Language Models
by: Enkhbayar, Tsogt-Ochir
Published: (2025)

Sparse PCA with False Discovery Rate Controlled Variable Selection
by: Machkour, Jasin, et al.
Published: (2024)

False Discovery Rate Control for Gaussian Graphical Models via Neighborhood Screening
by: Koka, Taulant, et al.
Published: (2024)

False Discovery Rate Control via Bayesian Mirror Statistic
by: Molinari, Marco, et al.
Published: (2025)

High-Dimensional False Discovery Rate Control for Dependent Variables
by: Machkour, Jasin, et al.
Published: (2024)

Asymptotic FDR Control with Model-X Knockoffs: Is Moments Matching Sufficient?
by: Fan, Yingying, et al.
Published: (2025)

Membership Inference Attacks with False Discovery Rate Control
by: Zhao, Chenxu, et al.
Published: (2025)

CatNet: Controlling the False Discovery Rate in LSTM with SHAP Feature Importance and Gaussian Mirrors
by: Han, Jiaan, et al.
Published: (2024)

False Discovery Rate Control via Frequentist-assisted Horseshoe
by: Liang, Qiaoyu, et al.
Published: (2025)

Learning False Discovery Rate Control via Model-Based Neural Networks
by: Vilella, Arnau, et al.
Published: (2026)

Do Sparse Autoencoders Identify Reasoning Features in Language Models?
by: Ma, George, et al.
Published: (2026)

Differentially Private Model-X Knockoffs via Johnson-Lindenstrauss Transform
by: Tao, Yuxuan, et al.
Published: (2025)

GRIP2: A Robust and Powerful Deep Knockoff Method for Feature Selection
by: Zou, Bob Junyi, et al.
Published: (2026)

Mean-Shift PCA by Knockoff Mean
by: Li, Mengda, et al.
Published: (2026)

Sparse Autoencoder Features for Classifications and Transferability
by: Gallifant, Jack, et al.
Published: (2025)

MonoSparse-CAM: Efficient Tree Model Processing via Monotonicity and Sparsity in CAMs
by: Molom-Ochir, Tergel, et al.
Published: (2024)

DeepDRK: Deep Dependency Regularized Knockoff for Feature Selection
by: Shen, Hongyu, et al.
Published: (2024)

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
by: Korznikov, Anton, et al.
Published: (2025)

Sparse Autoencoders Trained on the Same Data Learn Different Features
by: Paulo, Gonçalo, et al.
Published: (2025)

Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders
by: Marks, Luke, et al.
Published: (2024)

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders
by: Cao, Tue M., et al.
Published: (2026)

On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders
by: Simon, Elana, et al.
Published: (2026)

Adaptive Sparse Allocation with Mutual Choice & Feature Choice Sparse Autoencoders
by: Ayonrinde, Kola
Published: (2024)

Knockoffs Inference under Privacy Constraints
by: Cai, Zhanrui, et al.
Published: (2025)

SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models
by: Zhang, Mingxu, et al.
Published: (2026)

Rethinking Sparse Autoencoders: Select-and-Project for Fairness and Control from Encoder Features Alone
by: Bărbălau, Antonio, et al.
Published: (2025)

Sequential Knockoffs for Variable Selection in Reinforcement Learning
by: Ma, Tao, et al.
Published: (2023)

Learning Multi-Level Features with Matryoshka Sparse Autoencoders
by: Bussmann, Bart, et al.
Published: (2025)

MoRFI: Monotonic Sparse Autoencoder Feature Identification
by: Dimakopoulos, Dimitris, et al.
Published: (2026)

DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data
by: Kim, Taehyo, et al.
Published: (2023)

Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agent
by: Wang, Xinyuan, et al.
Published: (2024)

Feature Starvation as Geometric Instability in Sparse Autoencoders
by: Chaudhry, Faris, et al.
Published: (2026)

The Geometry of Concepts: Sparse Autoencoder Feature Structure
by: Li, Yuxiao, et al.
Published: (2024)

Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
by: Makelov, Aleksandar, et al.
Published: (2024)

Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders
by: Chanin, David, et al.
Published: (2025)

Beyond Fixed False Discovery Rates: Post-Hoc Conformal Selection with E-Variables
by: Zhu, Meiyi, et al.
Published: (2026)

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
by: Koromilas, Panagiotis, et al.
Published: (2026)

The Terminating-Random Experiments Selector: Fast High-Dimensional Variable Selection with False Discovery Rate Control
by: Machkour, Jasin, et al.
Published: (2021)