© 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. 95305
    Prev
    Next
    INDEX
    Explanations

    Code objects

    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
    +#
    -0.09
    ावर
    -0.08
    upal
    -0.08
     suyo
    -0.08
    ели
    -0.08
    :www
    -0.08
    \Auth
    -0.08
     vezi
    -0.08
    *sizeof
    -0.08
    Weekly
    -0.08
    POSITIVE LOGITS
    .from
    0.08
    (fetch
    0.07
    (p
    0.07
     мульт
    0.07
    (f
    0.07
     mistakenly
    0.07
     கூற
    0.06
     зазнач
    0.06
     uppsk
    0.06
     ലക്ഷ
    0.06
    Activations Density 0.001%

    No Known Activations