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. 102933
    Prev
    Next
    INDEX
    Explanations

    suggestions and tips

    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
     konie
    -0.07
    lad
    -0.07
     quale
    -0.07
     kap
    -0.07
    Btn
    -0.07
    Replies
    -0.07
    (signature
    -0.07
    awa
    -0.07
    !
    -0.07
    '}
    -0.07
    POSITIVE LOGITS
     detailing
    0.09
     throughout
    0.09
     подробно
    0.09
     Throughout
    0.09
    vendors
    0.09
     screenshots
    0.08
     specifics
    0.08
     fotógrafo
    0.08
     ذکر
    0.08
     detailed
    0.08
    Activations Density 0.091%

    No Known Activations