© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96282
    Prev
    Next
    INDEX
    Explanations

    say "sm" or "sp" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     honest
    -0.10
     Honest
    -0.10
     honesty
    -0.10
     misconduct
    -0.10
    作弊
    -0.10
     Cheat
    -0.09
    诚
    -0.09
     cheating
    -0.09
     Cheats
    -0.09
     ehrlich
    -0.09
    POSITIVE LOGITS
     spear
    0.10
     deep
    0.09
     Nigerian
    0.09
     throw
    0.09
    throw
    0.09
     romance
    0.09
     pek
    0.09
     rented
    0.09
     knock
    0.08
     dumpster
    0.08
    Activations Density 0.010%

    No Known Activations