© 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. 3-RESID-POST-AA
    11. 2567
    Prev
    Next
    INDEX
    Explanations

    cần

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raffin
    -0.08
    ?r
    -0.08
     ті
    -0.08
    tp
    -0.07
     मी
    -0.07
     eux
    -0.07
     comprob
    -0.07
     rheumatoid
    -0.07
    SO
    -0.07
     mantle
    -0.07
    POSITIVE LOGITS
     Hol
    0.08
    所得
    0.08
    وال
    0.08
     preg
    0.08
     Parr
    0.07
     �
    0.07
     Erin
    0.07
     пора
    0.07
    інен
    0.07
    Hol
    0.07
    Activations Density 0.019%

    No Known Activations