Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 74905
    Prev
    Next
    INDEX
    Explanations

    website article excerpts

    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
     therein
    -0.10
     Улар
    -0.09
     उसमें
    -0.09
     هى
    -0.09
     мыйзам
    -0.09
     Ў
    -0.09
    ервис
    -0.08
     ಎಸ್
    -0.08
     кызмат
    -0.08
     उनमें
    -0.08
    POSITIVE LOGITS
    Big
    0.07
     Therapeut
    0.07
    .release
    0.07
     Culture
    0.07
    Thank
    0.07
     terape
    0.07
     thank
    0.07
     Cocoa
    0.07
    ivent
    0.07
     :)↵↵
    0.07
    Activations Density 1.080%

    No Known Activations