© 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. 54799
    Prev
    Next
    INDEX
    Explanations

    2001: A Space Odyssey

    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
     oxide
    -0.08
    HTTPS
    -0.08
    fois
    -0.08
    sins
    -0.08
    instrument
    -0.07
    ouvrage
    -0.07
    slashes
    -0.07
    hb
    -0.07
     qualification
    -0.07
    folio
    -0.07
    POSITIVE LOGITS
     speech
    0.08
    积
    0.08
    齐
    0.08
    大小
    0.08
     kend
    0.08
    忆
    0.08
     overleg
    0.08
     tine
    0.08
     grandeur
    0.08
    คู่
    0.07
    Activations Density 0.002%

    No Known Activations