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. 54165
    Prev
    Next
    INDEX
    Explanations

    conserv

    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
    _condition
    -0.07
     облег
    -0.07
     доступ
    -0.07
    ducer
    -0.07
    नाम
    -0.07
    217
    -0.07
     subsid
    -0.07
     больше
    -0.07
    adaha
    -0.07
    Bd
    -0.07
    POSITIVE LOGITS
     remark
    0.07
     líqu
    0.07
    െയ്
    0.07
    servative
    0.07
     coward
    0.07
     conquer
    0.07
     virgin
    0.07
    Tong
    0.07
    กล
    0.07
    OKE
    0.07
    Activations Density 0.003%

    No Known Activations