© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102407
    Prev
    Next
    INDEX
    Explanations

    Character type checking

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    快播
    -0.09
    返水
    -0.08
     ratio
    -0.08
    ;background
    -0.08
     കുറഞ്ഞ
    -0.08
    啪
    -0.08
    ptus
    -0.08
     eliminated
    -0.08
     simplified
    -0.08
    ampling
    -0.08
    POSITIVE LOGITS
    isdigit
    0.22
    .is
    0.17
    ctype
    0.15
    Character
    0.15
     Character
    0.14
    字符
    0.13
    <Character
    0.13
     unicode
    0.12
    (Character
    0.12
    _char
    0.12
    Activations Density 0.002%

    No Known Activations