© 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. 91329
    Prev
    Next
    INDEX
    Explanations

    statements of intent

    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
     sache
    -0.08
    duk
    -0.07
     vin
    -0.07
    Sor
    -0.07
     sax
    -0.07
    gol
    -0.07
    Urg
    -0.07
    xes
    -0.07
    -duty
    -0.07
    /year
    -0.07
    POSITIVE LOGITS
    们
    0.10
    ๆ
    0.08
     hao
    0.08
    ിരിക്ക
    0.07
    y's
    0.07
    െങ്കിൽ
    0.07
    ается
    0.07
    under
    0.07
    ां
    0.07
    0.07
    Activations Density 0.300%
    No Known Activations