© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31313
    Prev
    Next
    INDEX
    Explanations

    Intensive care unit (ICU)

    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
    Cle
    -0.08
    osu
    -0.08
     grievances
    -0.08
     hemp
    -0.08
     văn
    -0.08
     comics
    -0.08
     Gregorian
    -0.07
    텍
    -0.07
    一年
    -0.07
     zie
    -0.07
    POSITIVE LOGITS
     sedation
    0.12
     cardiac
    0.11
     Monitoring
    0.11
     intensiv
    0.11
    Monitoring
    0.10
     monitoring
    0.10
     neon
    0.10
    监
    0.10
     neonatal
    0.09
     cardiovascular
    0.09
    Activations Density 0.028%

    No Known Activations