© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78431
    Prev
    Next
    INDEX
    Explanations

    lists to include

    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
    .elasticsearch
    -0.11
    _secs
    -0.09
     Louisiana
    -0.09
    /repos
    -0.09
     OSHA
    -0.09
    Boston
    -0.09
    шілі
    -0.09
     Tobago
    -0.09
     سوى
    -0.09
     Boston
    -0.09
    POSITIVE LOGITS
     anime
    0.11
     trope
    0.10
     Anime
    0.10
    动漫
    0.10
    Anime
    0.09
     manga
    0.09
    漫画
    0.09
     Japanese
    0.09
     일본
    0.08
     등장
    0.08
    Activations Density 0.011%

    No Known Activations