© 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. 553
    Prev
    Next
    INDEX
    Explanations

    entrainment phase

    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
    லி
    -0.08
    循环
    -0.07
    723
    -0.07
    leisten
    -0.07
    ‌ప
    -0.07
    ीज
    -0.07
    .match
    -0.07
     sportsbook
    -0.07
    _INTERVAL
    -0.07
     każde
    -0.07
    POSITIVE LOGITS
     Tamb
    0.09
     tweaking
    0.08
    Tamb
    0.08
     Koop
    0.08
    izing
    0.08
    isation
    0.08
    ization
    0.08
     Tou
    0.08
    inement
    0.08
    ising
    0.07
    Activations Density 0.001%

    No Known Activations