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. 9136
    Prev
    Next
    INDEX
    Explanations

    noise

    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
    ipr
    -0.09
     लाग
    -0.08
    寨
    -0.08
     pooled
    -0.08
     лип
    -0.08
     pharmacist
    -0.08
     उद्देश्य
    -0.08
    不可
    -0.08
    同行
    -0.08
     объектив
    -0.08
    POSITIVE LOGITS
     doing
    0.08
    ชาติ
    0.08
     asking
    0.08
    Checkbox
    0.08
    (handle
    0.07
     garbage
    0.07
     installer
    0.07
     aflevering
    0.07
    Installer
    0.07
     handle
    0.07
    Activations Density 0.002%

    No Known Activations