© 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. 68290
    Prev
    Next
    INDEX
    Explanations

    _ptr

    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
     canon
    -0.07
     rage
    -0.07
    -0.07
    治
    -0.07
     dresser
    -0.07
    Mail
    -0.07
    hren
    -0.07
     catég
    -0.07
    mail
    -0.07
     implanted
    -0.07
    POSITIVE LOGITS
     prepaid
    0.08
    =create
    0.08
     nois
    0.08
     influential
    0.08
     лам
    0.08
     Paramount
    0.07
     шав
    0.07
    (dic
    0.07
    ebu
    0.07
     مشک
    0.07
    Activations Density 0.001%
    No Known Activations