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. 19403
    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
     citing
    -0.08
    เมื่อ
    -0.08
    .WRAP
    -0.08
     negativa
    -0.08
    .ordinal
    -0.08
     Odisha
    -0.08
    _OCCURRED
    -0.08
     wanting
    -0.08
    .of
    -0.08
     بناء
    -0.07
    POSITIVE LOGITS
    .hpp
    0.11
    .h
    0.10
    .htm
    0.09
    .hxx
    0.09
    >
    ↵
    ↵
    0.09
    stdafx
    0.09
    /main
    0.09
    >↵↵//
    0.09
    stdint
    0.08
    >↵↵
    0.08
    Activations Density 0.003%

    No Known Activations