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

    Neuronpedia

    APICircuit 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. 12923
    Prev
    Next
    INDEX
    Explanations

    MiFID regulation

    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
     Fool
    -0.08
     Gordon
    -0.08
     tensor
    -0.08
     enforcement
    -0.08
     Tensor
    -0.08
    Tensor
    -0.08
     Amor
    -0.08
    ಾನು
    -0.07
     Bil
    -0.07
     Enforcement
    -0.07
    POSITIVE LOGITS
     aquello
    0.08
    உ
    0.08
    zew
    0.08
     odpow
    0.08
     puh
    0.08
    .small
    0.07
     прод
    0.07
     Californ
    0.07
    ismatic
    0.07
    sal
    0.07
    Activations Density 0.014%

    No Known Activations