© 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. 11-RESID-POST-AA
    11. 45430
    Prev
    Next
    INDEX
    Explanations

    essays

    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
     integrations
    -0.09
     workflows
    -0.08
     punch
    -0.08
     nenhuma
    -0.08
    Workflow
    -0.08
     ninguna
    -0.07
    してください
    -0.07
    下さい
    -0.07
     compliant
    -0.07
     выполнить
    -0.07
    POSITIVE LOGITS
     সমাজ
    0.11
    社会
    0.10
    ________
    0.10
     argued
    0.10
     evidenced
    0.10
     society
    0.10
     समाज
    0.10
     societal
    0.10
     considero
    0.10
     necessity
    0.09
    Activations Density 0.076%

    No Known Activations