Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54045
    Prev
    Next
    INDEX
    Explanations

    AI instructions/formatting

    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
    _driver
    -0.07
    driver
    -0.07
     differentiation
    -0.07
    -lg
    -0.07
    冷热
    -0.07
     Differ
    -0.07
     निक
    -0.07
    ache
    -0.07
     Drivers
    -0.07
     चालक
    -0.07
    POSITIVE LOGITS
     ظاهر
    0.10
    іны
    0.09
     trackers
    0.09
    יכים
    0.08
     kommentarer
    0.08
     」
    0.08
     dashed
    0.08
     Fool
    0.08
    렛
    0.08
     

    0.08
    Activations Density 0.090%

    No Known Activations