© 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. 2676
    Prev
    Next
    INDEX
    Explanations

    renewed

    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
     mirando
    -0.08
    pi
    -0.08
     Lord
    -0.07
     lord
    -0.07
     projected
    -0.07
    alls
    -0.07
     GMC
    -0.07
     updates
    -0.07
     daemon
    -0.07
     fund
    -0.07
    POSITIVE LOGITS
     impetus
    0.08
    imm
    0.08
    imbang
    0.08
     انگی
    0.07
     Fi
    0.07
     ضرورة
    0.07
    مس
    0.07
    ிம
    0.07
    경
    0.07
     Inhalt
    0.07
    Activations Density 0.002%

    No Known Activations