© 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. 8077
    Prev
    Next
    INDEX
    Explanations

    Archduke Franz Ferdinand

    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
     insulation
    -0.08
    重
    -0.08
    ‌ب
    -0.08
     శ
    -0.07
    tero
    -0.07
     insulating
    -0.07
    -0.07
     toler
    -0.07
     renewable
    -0.07
     mouvement
    -0.07
    POSITIVE LOGITS
     Drugs
    0.09
    mme
    0.09
     guns
    0.08
    (DIS
    0.08
     Българ
    0.08
     masina
    0.08
     Machines
    0.08
     Ofic
    0.08
     snakes
    0.08
     машине
    0.08
    Activations Density 0.001%
    No Known Activations