© 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. 75493
    Prev
    Next
    INDEX
    Explanations

    a

    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
     toll
    -0.09
     εισ
    -0.09
     возбуж
    -0.08
     崇
    -0.08
     обор
    -0.08
     geheel
    -0.08
     marched
    -0.08
     culto
    -0.08
    .Phone
    -0.08
     irrig
    -0.08
    POSITIVE LOGITS
     romant
    0.08
     plumbers
    0.08
     stm
    0.07
    อาหาร
    0.07
    消费
    0.07
    爱情
    0.07
    正在
    0.07
    (tuple
    0.07
    桌
    0.07
    St
    0.07
    Activations Density 0.019%

    No Known Activations