Author

Vladimir Menkov

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Interpretable GOHR Agents via Sparse Autoencoders

This work reports interpretability experiments for a tokenized autoregressive Transformer agent in the Game of Hidden Rules (GOHR), a compact two-rule task in which both hidden rules map object shapes to target buckets, but with different permutations.

Shiwei Tan, Yu-Song Zhao, Weiyi Qin et al. · arXiv.org · 0 citations