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. 60963
    Prev
    Next
    INDEX
    Explanations

    .,

    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
     basically
    -0.09
    則
    -0.08
    নৈতিক
    -0.08
     (=
    -0.08
     yani
    -0.08
    则
    -0.08
     また
    -0.07
     �
    -0.07
     --->
    -0.07
     nevertheless
    -0.07
    POSITIVE LOGITS
     Bach
    0.10
    Bah
    0.09
     Bah
    0.09
     funnel
    0.08
     Handel
    0.08
    meh
    0.08
     lining
    0.08
    Mil
    0.07
     Mil
    0.07
     माय
    0.07
    Activations Density 0.074%

    No Known Activations