© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12771
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     মতো
    -0.09
     Lange
    -0.08
    mol
    -0.08
     উদ্ব
    -0.08
     Cort
    -0.08
    unda
    -0.07
     под
    -0.07
     seg
    -0.07
    /.
    -0.07
     cortical
    -0.07
    POSITIVE LOGITS
     Adrian
    0.08
    和值
    0.08
    本文
    0.08
     роб
    0.07
     Editors
    0.07
     �
    0.07
    �
    0.07
     TObject
    0.07
     apr
    0.07
     Parker
    0.07
    Activations Density 0.005%

    No Known Activations