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. 19425
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Ձ
    -0.08
     વિચાર
    -0.08
     =
    -0.08
     Беларусь
    -0.08
    ddit
    -0.08
     Лукаш
    -0.08
    begin
    -0.08
    opf
    -0.07
    pendency
    -0.07
     գործընթաց
    -0.07
    POSITIVE LOGITS
    "?
    0.10
    ?↵↵
    0.10
    "?↵↵
    0.10
    了吗
    0.10
    」の
    0.10
    ??↵
    0.10
    ?",
    0.10
    .?
    0.09
    ☆↵↵
    0.09
    "))↵↵
    0.09
    Activations Density 0.428%

    No Known Activations