© 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. 26613
    Prev
    Next
    INDEX
    Explanations

    Exploration/exploitation tradeoff

    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
     Cancer
    -0.08
     Satin
    -0.07
    digest
    -0.07
    �
    -0.07
     Suspend
    -0.07
    _notify
    -0.07
    _digest
    -0.07
     tick
    -0.07
    _container
    -0.07
    _suspend
    -0.07
    POSITIVE LOGITS
     impulses
    0.09
    راح
    0.08
    ৃত
    0.08
     مو
    0.08
     વેપ
    0.08
     магазине
    0.08
     Laden
    0.07
     trades
    0.07
     economies
    0.07
    acji
    0.07
    Activations Density 0.001%

    No Known Activations