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. 58481
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
    lags
    -0.08
     steht
    -0.08
    免
    -0.08
    联
    -0.08
     联
    -0.08
     폐
    -0.08
    :last
    -0.08
     imun
    -0.08
    폐
    -0.07
     범
    -0.07
    POSITIVE LOGITS
    _album
    0.09
    album
    0.08
    現在
    0.08
    .meg
    0.08
     الحالي
    0.08
     الآن
    0.07
     тому
    0.07
     المقبل
    0.07
     manieren
    0.07
    -English
    0.07
    Activations Density 0.002%

    No Known Activations