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. 76481
    Prev
    Next
    INDEX
    Explanations

    window sill

    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
     headline
    -0.09
     Africans
    -0.09
    ජ
    -0.08
    ව
    -0.08
    Headline
    -0.08
     mega
    -0.08
    judul
    -0.08
    වත්
    -0.08
     bunch
    -0.07
     ගැන
    -0.07
    POSITIVE LOGITS
     দোক
    0.08
    -cart
    0.07
     lining
    0.07
    окат
    0.07
     countertops
    0.07
     quotidienne
    0.07
     पट
    0.07
     Oz
    0.07
     dagelijkse
    0.07
     Parker
    0.07
    Activations Density 0.002%

    No Known Activations