© 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. 47289
    Prev
    Next
    INDEX
    Explanations

    -

    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
    _ret
    -0.09
    $ret
    -0.09
    $user
    -0.08
     prominence
    -0.08
    iertos
    -0.08
     gauges
    -0.08
    ại
    -0.07
     пользователя
    -0.07
    Ret
    -0.07
    ret
    -0.07
    POSITIVE LOGITS
     sifat
    0.08
     antibi
    0.08
     sofr
    0.08
     poorest
    0.07
     robin
    0.07
     Sunday's
    0.07
     сын
    0.07
     zweimal
    0.07
     meister
    0.07
    ്ത്രീ
    0.07
    Activations Density 0.004%

    No Known Activations