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. 58681
    Prev
    Next
    INDEX
    Explanations

    ear pain

    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
    -0.08
     `.
    -0.08
     estado
    -0.07
     *
    -0.07
     Customer
    -0.07
     pozost
    -0.07
     overall
    -0.07
     middleware
    -0.07
    (mock
    -0.07
     positive
    -0.07
    POSITIVE LOGITS
    CHANGE
    0.10
     резко
    0.09
     voyage
    0.09
    utele
    0.09
    ACE
    0.09
     sudden
    0.09
     сә
    0.08
     kontak
    0.08
    contrast
    0.08
     hectic
    0.08
    Activations Density 0.002%

    No Known Activations