© 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. 7-RESID-POST-AA
    11. 1394
    Prev
    Next
    INDEX
    Explanations

    companies/organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calculator
    -0.08
    .Verify
    -0.08
    ホーム
    -0.08
    ERATOR
    -0.07
     puisque
    -0.07
     kien
    -0.07
    mf
    -0.07
     Tand
    -0.07
     règ
    -0.07
    ிருந்து
    -0.07
    POSITIVE LOGITS
     enfrent
    0.10
     facing
    0.09
     enfrentar
    0.09
    Facing
    0.08
     promedio
    0.08
     enfrenta
    0.08
     ఎదుర
    0.08
     faced
    0.08
     academics
    0.08
    面对
    0.07
    Activations Density 0.049%

    No Known Activations