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. 129749
    Prev
    Next
    INDEX
    Explanations

    language processing instructions

    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
     again
    -0.07
     Type
    -0.07
    rin
    -0.07
     the
    -0.07
     virg
    -0.07
     fresca
    -0.07
     π
    -0.07
     Peter
    -0.07
     sels
    -0.07
     Phys
    -0.06
    POSITIVE LOGITS
     ખેડ
    0.08
    בתי
    0.08
    នា
    0.08
     nominations
    0.08
    .prevent
    0.08
    emenangan
    0.08
     האָ
    0.08
     Northampton
    0.08
     waiter
    0.08
    atı
    0.08
    Activations Density 0.300%

    No Known Activations