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. 106255
    Prev
    Next
    INDEX
    Explanations

    Names in content generation requests

    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
    Эк
    -0.09
     taim
    -0.08
     którą
    -0.08
    issä
    -0.08
     notifications
    -0.08
     expo
    -0.08
     conversación
    -0.08
     textiles
    -0.08
     rtc
    -0.08
     Эк
    -0.08
    POSITIVE LOGITS
     célèbre
    0.11
     famous
    0.10
     celebrities
    0.10
     famosos
    0.10
    Celebrity
    0.10
     famoso
    0.10
     likeness
    0.10
     célè
    0.10
     célé
    0.09
     famously
    0.09
    Activations Density 0.144%

    No Known Activations