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. 77349
    Prev
    Next
    INDEX
    Explanations

    <|start|>

    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
    辅助
    -0.07
    产业
    -0.07
    谈
    -0.06
    Grass
    -0.06
    /community
    -0.06
     jumper
    -0.06
    :j
    -0.06
    -created
    -0.06
    antics
    -0.06
     vantage
    -0.06
    POSITIVE LOGITS
     Â
    0.10
     
    0.09
     
    0.08
     Δ
    0.08
    Â
    0.08
     ✔
    0.08
    是多少
    0.08
    rast
    0.08
     итог
    0.07
    �
    0.07
    Activations Density 41.602%

    No Known Activations