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

    Neuronpedia

    APICircuit 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. 12930
    Prev
    Next
    INDEX
    Explanations

    now

    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
    时候
    -0.09
     टाइम
    -0.09
     võib
    -0.08
     terrorists
    -0.08
     aussi
    -0.08
     Fue
    -0.08
     अपराध
    -0.08
    ɵ
    -0.08
     toimub
    -0.08
     الإرهاب
    -0.08
    POSITIVE LOGITS
     nodded
    0.08
    leggen
    0.07
     tic
    0.07
    Sap
    0.07
    Wishlist
    0.07
    رة
    0.07
    .Move
    0.07
     Rana
    0.07
     eie
    0.07
     neck
    0.07
    Activations Density 0.000%

    No Known Activations