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. 15-RESID-POST-AA
    6. 189
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hypothetical
    -0.08
    Mat
    -0.08
     prova
    -0.07
    .must
    -0.07
     restrict
    -0.07
     mat
    -0.07
     boasts
    -0.07
     remedies
    -0.07
     spéc
    -0.07
     would
    -0.07
    POSITIVE LOGITS
     Parece
    0.12
     parece
    0.11
     Increase
    0.11
     increasing
    0.11
     Increasing
    0.11
     schein
    0.11
     aparentemente
    0.10
     parecía
    0.10
    越来越
    0.10
     aumento
    0.10
    Activations Density 0.019%

    No Known Activations