Author

A. Shevchenko

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.

#artificial intelligence Preprint Sep 2026

Local Sparsity Enables Unsupervised LLM Safety Detection

This work proposes a framework for locally masked SAE-based anomaly detection, supported by theoretical justifications, and demonstrates their ability to capture meaningful safety information while using only 1-2% of SAE neurons for computation.

Xin Chen, Gil Kur, A. Shevchenko et al. · 0 citations