© 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. 30954
    Prev
    Next
    INDEX
    Explanations

    legal codes

    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
    万美元
    -0.10
     Reese
    -0.10
    Seattle
    -0.09
    亿美元
    -0.09
     Seattle
    -0.08
     Arkansas
    -0.08
     zy
    -0.08
    
    -0.08
     reef
    -0.08
    退款
    -0.08
    POSITIVE LOGITS
     Guido
    0.11
     codice
    0.11
    (nome
    0.11
     Luigi
    0.10
     italian
    0.10
    Italian
    0.10
     Milan
    0.10
     Regione
    0.10
     Italian
    0.10
     Itali
    0.09
    Activations Density 0.039%

    No Known Activations