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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 68236
    Prev
    Next
    INDEX
    Explanations

    Colosseum and gladiators

    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
     Lip
    -0.08
    -ln
    -0.08
     Liqu
    -0.08
     ঢ
    -0.08
    _global
    -0.08
    _ln
    -0.08
    /local
    -0.08
     Laz
    -0.07
    Lip
    -0.07
     Subl
    -0.07
    POSITIVE LOGITS
     fx
    0.08
    læ
    0.08
    èles
    0.08
     للا
    0.08
     Welch
    0.08
     бро
    0.08
     openings
    0.07
     Sert
    0.07
     malpractice
    0.07
     scrape
    0.07
    Activations Density 0.001%

    No Known Activations