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. 75130
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     norms
    -0.08
     Danish
    -0.08
     Normandy
    -0.07
    Daddy
    -0.07
     mainland
    -0.07
     reflected
    -0.07
    .exports
    -0.07
     danske
    -0.07
    ざ
    -0.07
    -origin
    -0.07
    POSITIVE LOGITS
    勿
    0.08
    _xlabel
    0.08
     predictor
    0.08
    :Y
    0.08
    跨度
    0.08
     ಪೂ
    0.08
     الإث
    0.07
     качестве
    0.07
    键
    0.07
     predictors
    0.07
    Activations Density 0.003%

    No Known Activations