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. 60402
    Prev
    Next
    INDEX
    Explanations

    prediction accuracy

    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
    (_,
    -0.09
     soak
    -0.08
     lume
    -0.07
    <|reserved_200010|>
    -0.07
    bod
    -0.07
     idee
    -0.07
     đóng
    -0.07
    ale
    -0.07
    лес
    -0.07
    уються
    -0.07
    POSITIVE LOGITS
     accuracy
    0.23
     Accuracy
    0.22
    Accuracy
    0.21
    _accuracy
    0.20
    accuracy
    0.20
     accur
    0.19
    准确
    0.18
     Genau
    0.16
     precisión
    0.15
     precisão
    0.15
    Activations Density 0.026%

    No Known Activations