© 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. 11-RESID-POST-AA
    11. 108675
    Prev
    Next
    INDEX
    Explanations

    Random information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \↵
    -0.08
     salari
    -0.08
     java
    -0.08
     '''↵
    -0.07
     participated
    -0.07
     &↵
    -0.07
     Bert
    -0.07
     //↵
    -0.07
    ੂੰ
    -0.07
     februari
    -0.07
    POSITIVE LOGITS
     vorstellen
    0.08
    ypse
    0.08
     인해
    0.08
    ;(
    0.08
     باعث
    0.08
     видеть
    0.08
     justamente
    0.08
     있기
    0.08
     thus
    0.08
    КА
    0.08
    Activations Density 0.536%

    No Known Activations