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. 120264
    Prev
    Next
    INDEX
    Explanations

    military/defense

    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
     Gatsby
    -0.11
     Etsy
    -0.10
     candies
    -0.10
     eateries
    -0.10
     Airbnb
    -0.10
     яб
    -0.10
    美容
    -0.10
     emojis
    -0.09
     Goodreads
    -0.09
     restaurants
    -0.09
    POSITIVE LOGITS
     NATO
    0.19
     Tactical
    0.17
     missile
    0.16
     सैनिक
    0.15
     tactical
    0.15
     commanders
    0.15
     reconnaissance
    0.14
     briefing
    0.14
     infantry
    0.14
     UAV
    0.13
    Activations Density 0.157%

    No Known Activations