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. 53891
    Prev
    Next
    INDEX
    Explanations

    pixel

    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
    巴黎
    -0.09
    פי
    -0.08
     decret
    -0.08
     Heathrow
    -0.08
    ும்ப
    -0.08
    .Invocation
    -0.08
     opér
    -0.08
    出票
    -0.08
     Handicap
    -0.07
     promis
    -0.07
    POSITIVE LOGITS
     રંગ
    0.10
     DOS
    0.09
     रंग
    0.09
    pixel
    0.09
    Pixel
    0.09
     kolor
    0.09
     彩
    0.09
     anime
    0.09
    grain
    0.09
     colorful
    0.08
    Activations Density 0.006%

    No Known Activations