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. 102553
    Prev
    Next
    INDEX
    Explanations

    acting roles

    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
    য
    -0.08
    rometer
    -0.08
     transmisión
    -0.07
    Из
    -0.07
    _google
    -0.07
    regexp
    -0.07
    Re
    -0.07
     регуляр
    -0.07
     spilling
    -0.07
     Из
    -0.07
    POSITIVE LOGITS
    猎
    0.09
    .WEST
    0.08
    .roles
    0.08
    角色
    0.08
    portun
    0.08
     ಪಾತ್ರ
    0.08
     పాత్ర
    0.08
    roles
    0.08
    (enemy
    0.07
     portraying
    0.07
    Activations Density 0.019%

    No Known Activations