© 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. 47334
    Prev
    Next
    INDEX
    Explanations

    keep

    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
    ूम
    -0.09
    _\
    -0.07
    518
    -0.07
    ителями
    -0.07
    ителям
    -0.07
     és
    -0.07
    otiv
    -0.07
    итель
    -0.07
    ിമ
    -0.07
    information
    -0.07
    POSITIVE LOGITS
     sostuvo
    0.08
     detr
    0.08
    品质
    0.08
     enemigos
    0.08
     droge
    0.08
    0.08
     rapidez
    0.08
     zwarte
    0.08
     dhan
    0.08
     ശ്രദ്ധ
    0.07
    Activations Density 0.004%
    No Known Activations