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. 11-RESID-POST-AA
    6. 43843
    Prev
    Next
    INDEX
    Explanations

    URL encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mor
    -0.10
     Xiao
    -0.09
    Cov
    -0.08
    _cov
    -0.08
    CMP
    -0.08
     dispos
    -0.08
     qan
    -0.08
     warming
    -0.08
    Mor
    -0.08
    bounds
    -0.08
    POSITIVE LOGITS
    Unicode
    0.13
     문자열
    0.13
    .escape
    0.13
     Unicode
    0.13
    字符串
    0.12
     unicode
    0.12
     ASCII
    0.12
     punctuation
    0.12
     urlencode
    0.12
     escaped
    0.12
    Activations Density 0.007%

    No Known Activations