Preprint
Aug 2026
CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits
CircuitSteer is introduced, a novel framework that leverages Sparse Autoencoders (SAEs) to identify and manipulate coherent semantic circuits distributed across multiple layers that yields strictly more robust and effective behavioral control than static single-point interventions.
Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad et al.
· 1 citation