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. 43157
    Prev
    Next
    INDEX
    Explanations

    Statistical measures

    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
     bry
    -0.08
     Mormon
    -0.08
     Supervisor
    -0.07
     dah
    -0.07
     hindu
    -0.07
     Buddhist
    -0.07
     FOX
    -0.07
     Baptist
    -0.07
    upar
    -0.07
    kenn
    -0.07
    POSITIVE LOGITS
    <>("
    0.08
     voix
    0.08
     ఉంట
    0.08
    Navig
    0.07
     계산
    0.07
     �
    0.07
     오류
    0.07
    ="//
    0.07
    imax
    0.07
     ఉన్నాయి
    0.07
    Activations Density 0.001%

    No Known Activations