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. 15-RESID-POST-AA
    6. 19428
    Prev
    Next
    INDEX
    Explanations

    ographic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     చూ�
    -0.08
     jeung
    -0.08
    adii
    -0.08
     temperaturas
    -0.07
     zo
    -0.07
     tasas
    -0.07
     viim
    -0.07
     ����
    -0.07
     ...…↵
    -0.07
     vim
    -0.07
    POSITIVE LOGITS
     بشكل
    0.09
    -like
    0.09
     العالي
    0.08
     alike
    0.08
     등
    0.08
     ஆகிய
    0.08
    など
    0.08
     "#
    0.08
     ("
    0.08
     등의
    0.08
    Activations Density 0.003%

    No Known Activations