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. 60619
    Prev
    Next
    INDEX
    Explanations

    Chinese scientific text

    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
     entfernen
    -0.09
     closets
    -0.08
     removal
    -0.08
     removes
    -0.08
     제거
    -0.08
     サイズ
    -0.08
     ಉಪಸ್ಥ
    -0.08
    anar
    -0.08
     verwijderen
    -0.08
    юк
    -0.08
    POSITIVE LOGITS
    创新
    0.11
    科研
    0.11
    公益
    0.10
    党建
    0.10
     excellence
    0.09
    公众号
    0.09
    Innovation
    0.09
    寓
    0.09
    出台
    0.08
    思
    0.08
    Activations Density 0.027%

    No Known Activations