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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60648
    Prev
    Next
    INDEX
    Explanations

    math; assistant messages

    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
    rf
    -0.09
     sme
    -0.08
    \Console
    -0.08
     casualty
    -0.08
     nause
    -0.08
    ereich
    -0.07
     neur
    -0.07
     manc
    -0.07
     Prof
    -0.07
     parecer
    -0.07
    POSITIVE LOGITS
    matically
    0.08
     caramel
    0.08
     eq
    0.08
     aur
    0.07
     connective
    0.07
     uc
    0.07
     pää
    0.07
    096
    0.07
    matic
    0.07
     karşı
    0.07
    Activations Density 0.019%

    No Known Activations