© 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. 45311
    Prev
    Next
    INDEX
    Explanations

    .FC

    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
    _ga
    -0.08
     steady
    -0.08
     sinus
    -0.08
     haar
    -0.07
    こちら
    -0.07
     gelukkig
    -0.07
     GA
    -0.07
    ga
    -0.07
     planner
    -0.07
     Squ
    -0.07
    POSITIVE LOGITS
     ()
    0.09
    (parameters
    0.09
    (currency
    0.09
    (com
    0.08
    <ID
    0.08
    (review
    0.08
    (configuration
    0.08
     entails
    0.08
    (cfg
    0.08
     그렇게
    0.08
    Activations Density 0.002%

    No Known Activations