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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 75213
    Prev
    Next
    INDEX
    Explanations

    animal behavior and habitat

    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
     sequential
    -0.07
     sequência
    -0.07
    Append
    -0.07
    lemek
    -0.07
     sewing
    -0.07
     получилось
    -0.07
     músc
    -0.07
     tabletop
    -0.07
     futurs
    -0.07
     mee
    -0.07
    POSITIVE LOGITS
     migrate
    0.11
     noct
    0.11
     migr
    0.11
    迁
    0.11
     migrated
    0.10
     hunted
    0.10
     بالقرب
    0.10
     attracted
    0.10
     sightings
    0.10
     verbringen
    0.10
    Activations Density 0.023%

    No Known Activations