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. 76097
    Prev
    Next
    INDEX
    Explanations

    wonder

    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
     uc
    -0.08
     Sauv
    -0.07
     ответствен
    -0.07
    予定
    -0.07
    orbit
    -0.07
    primitive
    -0.07
     moi
    -0.07
     throm
    -0.07
     dikenal
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     aloud
    0.10
    一下
    0.10
     wondering
    0.10
     wondered
    0.10
     પૂછ
    0.09
     Kendall
    0.09
    פק
    0.08
    究
    0.08
     לגבי
    0.08
    别人
    0.08
    Activations Density 0.011%

    No Known Activations