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. 43283
    Prev
    Next
    INDEX
    Explanations

    as

    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
    an
    -0.08
     griff
    -0.07
    ВС
    -0.07
    ({"
    -0.07
    DAP
    -0.07
    -per
    -0.07
     Noble
    -0.07
     hailed
    -0.07
    onsense
    -0.07
    (an
    -0.06
    POSITIVE LOGITS
     nhau
    0.10
    กัน
    0.08
    去年
    0.08
     Gw
    0.08
     Advocacy
    0.08
     applying
    0.08
    輸
    0.08
     Vou
    0.08
     makin
    0.08
    就是说
    0.08
    Activations Density 0.014%

    No Known Activations