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. 19304
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     ՝
    -0.11
     аҿ
    -0.10
     vulavula
    -0.10
     cluichí
    -0.10
     йеңи
    -0.10
     cluiche
    -0.10
     иазкны
    -0.10
     ҿыц
    -0.10
     հոդված
    -0.10
    ҳое
    -0.10
    POSITIVE LOGITS
     and
    0.11
    そして
    0.10
     ਅਤੇ
    0.10
     आणि
    0.09
    この
    0.08
     và
    0.08
    <|reserved_200016|>
    0.08
    และ
    0.08
     dessa
    0.08
     tohoto
    0.08
    Activations Density 0.047%

    No Known Activations