Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 46132
    Prev
    Next
    INDEX
    Explanations

    angle

    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
    Tank
    -0.08
     setter
    -0.08
    bank
    -0.08
    Ter
    -0.08
     xc
    -0.07
     sauveg
    -0.07
    loggen
    -0.07
     xl
    -0.07
     serialize
    -0.07
     Toy
    -0.07
    POSITIVE LOGITS
     regla
    0.09
    睛
    0.08
    _angles
    0.08
     cuota
    0.08
     Cro
    0.08
     françaises
    0.08
     Reglamento
    0.08
     Angle
    0.08
     olsa
    0.08
     profesora
    0.08
    Activations Density 0.001%

    No Known Activations