© 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. 75594
    Prev
    Next
    INDEX
    Explanations

    Historical facts and dates

    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
     worlds
    -0.08
     aromas
    -0.07
     Shorts
    -0.07
    erías
    -0.07
    istemas
    -0.07
     ret
    -0.07
     rer
    -0.07
    äumen
    -0.07
     പൂ
    -0.07
    .decorators
    -0.07
    POSITIVE LOGITS
     Sala
    0.08
     pq
    0.08
     sels
    0.08
    328
    0.08
     Petro
    0.07
    онов
    0.07
    Union
    0.07
     Kost
    0.07
     zas
    0.07
     Bron
    0.07
    Activations Density 0.041%

    No Known Activations