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. 53820
    Prev
    Next
    INDEX
    Explanations

    is

    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
     інш
    -0.09
     dedicada
    -0.08
     другого
    -0.08
     изготов
    -0.08
     xem
    -0.08
     лицо
    -0.07
    (Material
    -0.07
    itä
    -0.07
     другую
    -0.07
     hepatic
    -0.07
    POSITIVE LOGITS
     nao
    0.08
    雅
    0.08
    -alpha
    0.08
    违
    0.08
    �
    0.08
     ош
    0.08
    _alpha
    0.08
    .PERM
    0.08
    เจ
    0.08
    абар
    0.07
    Activations Density 0.000%

    No Known Activations