© 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. 78498
    Prev
    Next
    INDEX
    Explanations

    Russian

    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
     resurf
    -0.08
    🏼
    -0.08
    cknowled
    -0.08
    /PT
    -0.08
    柳
    -0.08
    _RES
    -0.07
     ayaan
    -0.07
    ಕ್ಕೆ
    -0.07
     Rout
    -0.07
     ros
    -0.07
    POSITIVE LOGITS
     जब
    0.10
     alte
    0.09
     свою
    0.08
     oc
    0.08
     свои
    0.08
     cons
    0.08
     �
    0.08
     تو
    0.08
     germ
    0.08
     свой
    0.08
    Activations Density 0.076%

    No Known Activations