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. 19172
    Prev
    Next
    INDEX
    Explanations

    data and structure

    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
     떠
    -0.09
    玩吗
    -0.08
     Αυτό
    -0.07
    ?,↵
    -0.07
     또
    -0.07
     '\'
    -0.07
     €,
    -0.07
    ەم
    -0.07
    ?:
    -0.07
    "?↵↵
    -0.07
    POSITIVE LOGITS
     sinne
    0.09
    -
    0.09
    :首页
    0.09
     preferable
    0.08
     sod
    0.08
    .nav
    0.08
     sannan
    0.08
     farko
    0.08
    ropic
    0.08
     счит
    0.08
    Activations Density 0.000%

    No Known Activations