Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74624
    Prev
    Next
    INDEX
    Explanations

    :

    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
    yii
    -0.07
     doctrine
    -0.07
    iro
    -0.07
    Cfg
    -0.07
    双
    -0.07
    .cfg
    -0.07
     Ivy
    -0.07
    HP
    -0.07
    -logo
    -0.06
     stepping
    -0.06
    POSITIVE LOGITS
     아니라
    0.08
    なく
    0.08
     сумма
    0.08
    잠
    0.08
     評
    0.08
     JES
    0.08
     ગણ
    0.08
     jailed
    0.08
     wors
    0.08
     paralysis
    0.08
    Activations Density 0.021%

    No Known Activations