Cover Image

Distribution-Aware Feature Selection for SAEs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Oozeer, Narmeen, Prakash, Nirmalendu, Lan, Michael, Rigg, Alice, Abdullah, Amirali
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

Bilinear Convolution Decomposition for Causal RL Interpretability
by: Oozeer, Narmeen, et al.
Published: (2024)

DreamReader: An Interpretability Toolkit for Text-to-Image Models
by: Prakash, Nirmalendu, et al.
Published: (2026)

Activation Space Interventions Can Be Transferred Between Large Language Models
by: Oozeer, Narmeen, et al.
Published: (2025)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
by: Oozeer, Narmeen, et al.
Published: (2025)

Understanding and Mitigating Dataset Corruption in LLM Steering
by: Anderson, Cullen, et al.
Published: (2026)

Spectral Superposition: A Theory of Feature Geometry
by: Ivanov, Georgi, et al.
Published: (2026)

SAEs Are Good for Steering -- If You Select the Right Features
by: Arad, Dana, et al.
Published: (2025)

Converting MLPs into Polynomials in Closed Form
by: Belrose, Nora, et al.
Published: (2025)

Weight-based Decomposition: A Case for Bilinear MLPs
by: Pearce, Michael T., et al.
Published: (2024)

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
by: Roytburg, Dani, et al.
Published: (2025)

Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
by: Roytburg, Dani, et al.
Published: (2026)

Features Emerge as Discrete States: The First Application of SAEs to 3D Representations
by: Miao, Albert, et al.
Published: (2025)

Tokenized SAEs: Disentangling SAE Reconstructions
by: Dooms, Thomas, et al.
Published: (2025)

The Rate-Distortion-Polysemanticity Tradeoff in SAEs
by: Mencattini, Tommaso, et al.
Published: (2026)

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
by: Song, Xiangchen, et al.
Published: (2025)

Analyzing (In)Abilities of SAEs via Formal Languages
by: Menon, Abhinav, et al.
Published: (2024)

Bilinear MLPs enable weight-based mechanistic interpretability
by: Pearce, Michael T., et al.
Published: (2024)

Residual Stream Analysis with Multi-Layer SAEs
by: Lawson, Tim, et al.
Published: (2024)

Approximating Human Preferences Using a Multi-Judge Learned System
by: Sprejer, Eitán, et al.
Published: (2025)

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
by: Korznikov, Anton, et al.
Published: (2026)

Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design
by: Brzozowski, Michał, et al.
Published: (2026)

Resa: Transparent Reasoning Models via SAEs
by: Wang, Shangshang, et al.
Published: (2025)

Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs
by: Ayonrinde, Kola, et al.
Published: (2024)

Structure-Aware Masking for Protein Representation Learning
by: Walton, Thomas, et al.
Published: (2026)

Can SAEs reveal and mitigate racial biases of LLMs in healthcare?
by: Ahsan, Hiba, et al.
Published: (2025)

Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs
by: Lee, Daniel J., et al.
Published: (2024)

Teach Old SAEs New Domain Tricks with Boosting
by: Koriagin, Nikita, et al.
Published: (2025)

Distributionally Robust Feature Selection
by: Swaroop, Maitreyi, et al.
Published: (2025)

Detecting and Characterizing Planning in Language Models
by: Nainani, Jatin, et al.
Published: (2025)

Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering
by: Prakash, Nirmalendu, et al.
Published: (2026)

A Context-Aware Temporal Modeling through Unified Multi-Scale Temporal Encoding and Hierarchical Sequence Learning for Single-Channel EEG Sleep Staging
by: Vakili, Amirali, et al.
Published: (2025)

Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models
by: Simbeck, Katharina, et al.
Published: (2025)

Causally-Aware Unsupervised Feature Selection Learning
by: Shen, Zongxin, et al.
Published: (2024)

A Multicollinearity-Aware Signal-Processing Framework for Cross-$β$ Identification via X-ray Scattering of Alzheimer's Tissue
by: Bashit, Abdullah Al, et al.
Published: (2025)

Sycophancy as compositions of Atomic Psychometric Traits
by: Jain, Shreyans, et al.
Published: (2025)

Minimax and Communication-Efficient Distributed Best Subset Selection with Oracle Property
by: Lan, Jingguo, et al.
Published: (2024)

Safe Distributionally Robust Feature Selection under Covariate Shift
by: Hanada, Hiroyuki, et al.
Published: (2026)

Effective Feature Selection for Predicting Spreading Factor with ML in Large LoRaWAN-based Mobile IoT Networks
by: Prakash, Aman, et al.
Published: (2025)

Scalable Expressiveness through Preprocessed Graph Perturbations
by: Saber, Danial, et al.
Published: (2024)

RADE: Random Add-Drop Edge as a Regularizer
by: Saber, Danial, et al.
Published: (2026)