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. 55824
    Prev
    Next
    INDEX
    Explanations

    Code commenting

    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
     sok
    -0.09
    illante
    -0.07
     seal
    -0.07
    /dat
    -0.07
     secret
    -0.07
     зна
    -0.07
     intérieure
    -0.07
     ADV
    -0.07
     Approx
    -0.07
    acji
    -0.07
    POSITIVE LOGITS
    াহত
    0.08
     MART
    0.08
    atig
    0.08
    Mart
    0.08
    vars
    0.08
     Mail
    0.08
    -MM
    0.08
    _MAIL
    0.07
     навед
    0.07
     Ville
    0.07
    Activations Density 0.002%

    No Known Activations