© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1161
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     चीज
    -0.08
    冷
    -0.08
     وف
    -0.08
    .Parameters
    -0.08
     सारी
    -0.08
     conveniently
    -0.07
     chia
    -0.07
     शुरुआत
    -0.07
    ಿಟ್ಟ
    -0.07
    闪
    -0.07
    POSITIVE LOGITS
     vegetation
    0.09
    Interpret
    0.08
     Vere
    0.07
     debate
    0.07
    Inference
    0.07
    contro
    0.07
    _income
    0.07
     metav
    0.07
    人为
    0.07
    reinterpret
    0.07
    Activations Density 0.035%

    No Known Activations