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. 65770
    Prev
    Next
    INDEX
    Explanations

    alcohol and health

    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
     exhausting
    -0.08
     unr
    -0.08
     unfamiliar
    -0.08
     affront
    -0.07
     presentatie
    -0.07
     Karen
    -0.07
     fierce
    -0.07
     kë
    -0.07
     authority
    -0.07
     Euskal
    -0.07
    POSITIVE LOGITS
    atonin
    0.10
     safest
    0.09
    safe
    0.08
    bucket
    0.08
     analges
    0.08
    benef
    0.08
    dol
    0.08
     analizar
    0.08
    ");↵↵/
    0.08
     beneficial
    0.08
    Activations Density 0.009%

    No Known Activations