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. 19348
    Prev
    Next
    INDEX
    Explanations

    counting

    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
     the
    -0.10
     ҳар
    -0.09
    .↵↵
    -0.09
     vess
    -0.08
     فى
    -0.08
     véc
    -0.08
     المؤمن
    -0.08
     怎样
    -0.08
    ديق
    -0.08
    اسين
    -0.08
    POSITIVE LOGITS
     Ltd
    0.08
    intro
    0.08
    /ns
    0.08
    ⭐
    0.08
     intro
    0.08
    ifs
    0.08
    -worthy
    0.08
    👍
    0.07
    $ret
    0.07
     ✔
    0.07
    Activations Density 0.025%

    No Known Activations