© 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. 91381
    Prev
    Next
    INDEX
    Explanations

    Russian and "such"

    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
     neug
    -0.08
    ხედ
    -0.08
     Rau
    -0.08
    安县
    -0.08
     kne
    -0.08
     tast
    -0.07
     Lü
    -0.07
     Meetup
    -0.07
    יגע
    -0.07
    tragen
    -0.07
    POSITIVE LOGITS
     Mona
    0.07
     animation
    0.07
    .images
    0.07
    animate
    0.07
     图片
    0.07
    (images
    0.07
     anime
    0.07
    ాన్స్
    0.07
     animate
    0.07
     confirmations
    0.06
    Activations Density 0.001%

    No Known Activations