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. 27599
    Prev
    Next
    INDEX
    Explanations

    Coefficient of determination

    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
     condem
    -0.09
    .flags
    -0.08
     Breizh
    -0.08
     condemn
    -0.08
     Afghanistan
    -0.08
     condam
    -0.08
    Flags
    -0.08
    ixon
    -0.07
     Appreciate
    -0.07
     vidé
    -0.07
    POSITIVE LOGITS
     squares
    0.09
     square
    0.09
     squared
    0.09
    ุม
    0.08
     stores
    0.08
    QUARE
    0.08
    _squared
    0.08
     Squares
    0.08
    _square
    0.08
     квадрат
    0.08
    Activations Density 0.024%

    No Known Activations