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. 120396
    Prev
    Next
    INDEX
    Explanations

    exercise

    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
     механизм
    -0.08
     obligation
    -0.08
     ideological
    -0.08
     obligations
    -0.08
     Authorization
    -0.08
     дир
    -0.07
    Copyright
    -0.07
     अधिकार
    -0.07
     Nobel
    -0.07
     inscription
    -0.07
    POSITIVE LOGITS
     sederhana
    0.10
     sencilla
    0.10
     rowing
    0.09
     sauté
    0.09
     sencillo
    0.09
    .tsv
    0.09
     gentle
    0.09
     piccoli
    0.09
     gardening
    0.09
     thighs
    0.09
    Activations Density 0.012%

    No Known Activations