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. 60626
    Prev
    Next
    INDEX
    Explanations

    conversations and reasoning

    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
                               
    -0.07
     لک
    -0.07
    بيض
    -0.07
    ishly
    -0.07
     lungs
    -0.07
    ',"
    -0.07
    您好
    -0.07
    aaaa
    -0.07
     pik
    -0.07
    密码
    -0.07
    POSITIVE LOGITS
    (collection
    0.09
     coleção
    0.08
     совсем
    0.08
    \Builder
    0.08
    _COLLECTION
    0.08
    Rés
    0.08
    etect
    0.07
     raakt
    0.07
     испыт
    0.07
    ಿಷ್ಠ
    0.07
    Activations Density 0.001%

    No Known Activations