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. 113033
    Prev
    Next
    INDEX
    Explanations

    quoted text

    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
     binary
    -0.09
    binary
    -0.08
     IDs
    -0.08
     domác
    -0.07
    inetic
    -0.07
     headers
    -0.07
    Binary
    -0.07
     subscriptions
    -0.07
     Forex
    -0.07
     ataques
    -0.07
    POSITIVE LOGITS
     interviewed
    0.11
     বলেছেন
    0.11
     అన్నారు
    0.10
     ಹೇಳಿದ್ದಾರೆ
    0.10
     quoted
    0.10
     ಹೇಳಿದರು
    0.09
    采访
    0.09
     বলেন
    0.09
    ,we
    0.09
     comentó
    0.09
    Activations Density 0.344%

    No Known Activations