© 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. 47907
    Prev
    Next
    INDEX
    Explanations

    student

    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
     caused
    -0.07
    ，同比
    -0.07
    ОВ
    -0.07
     Beyond
    -0.07
     lost
    -0.07
     quizzes
    -0.06
    殊
    -0.06
    ติด
    -0.06
     decrease
    -0.06
    Ч
    -0.06
    POSITIVE LOGITS
     acteur
    0.09
     navigator
    0.08
     محور
    0.08
    :innen
    0.08
    主体
    0.08
    -led
    0.08
    anyị
    0.08
     adolescent
    0.08
     autistic
    0.08
    -forward
    0.08
    Activations Density 0.013%

    No Known Activations