Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Aleksandar Makelov, Georg Lange, Neel Nanda
2/12/2026

No confident code implementation found for this paper. 3 possible matches can be shown below.

Semantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Making Visual Sense of Oracle Bones for You and Me

100% match2026

An Optimal Control View of LoRA and Binary Controller Design for Vision Transformers

97% match2026

PEACE: A Dataset of Pharmaceutical Care for Cancer Pain Analgesia Evaluation and Medication Decision

96% match2026

Century: A Framework and Dataset for Evaluating Historical Contextualisation of Sensitive Images

96% match2026

Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs

96% match2 repos62026

FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning

95% match2026

Cite this paper

@article{makelov2026towards,
  title  = {Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control},
  author = {Aleksandar Makelov and Georg Lange and Neel Nanda},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:101f98fa7fdaf338fe5e3c492903c31f633b4f0c},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/101f98fa7fdaf338fe5e3c492903c31f633b4f0c.svg)](https://codeofpaper.com/paper/101f98fa7fdaf338fe5e3c492903c31f633b4f0c)

Discussion