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. 56053
    Prev
    Next
    INDEX
    Explanations

    Super Bowl

    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
    /pass
    -0.08
    .dep
    -0.08
     �
    -0.08
     густ
    -0.08
    .cut
    -0.07
    ง
    -0.07
    �
    -0.07
    вон
    -0.07
    iro
    -0.07
    Correction
    -0.07
    POSITIVE LOGITS
    广告
    0.08
     раз
    0.08
    影片
    0.08
    视频
    0.08
     विज्ञ
    0.08
     remport
    0.08
     Winner
    0.08
     Extras
    0.07
     Vide
    0.07
     winner
    0.07
    Activations Density 0.004%

    No Known Activations