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. 43227
    Prev
    Next
    INDEX
    Explanations

    app store commissions

    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
    (color
    -0.08
    [color
    -0.08
    εδ
    -0.08
     unpredict
    -0.07
    .ve
    -0.07
     color
    -0.07
    athed
    -0.07
    ,color
    -0.07
     appe
    -0.07
    alarda
    -0.07
    POSITIVE LOGITS
     शुल्क
    0.16
    手续费
    0.13
    费用
    0.12
     फीस
    0.12
     fees
    0.11
     खर्च
    0.11
     Fees
    0.11
    Fees
    0.11
     Gebühren
    0.11
     هزینه
    0.10
    Activations Density 0.019%

    No Known Activations