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

    Neuronpedia

    Jacobian LensNEW
    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. 112459
    Prev
    Next
    INDEX
    Explanations

    Superstitions

    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
    latest
    -0.08
    LATEST
    -0.08
    chon
    -0.08
     Writable
    -0.07
     nicotine
    -0.07
    carbon
    -0.07
     திட்ட
    -0.07
    baseline
    -0.07
    -rate
    -0.07
    rate
    -0.07
    POSITIVE LOGITS
     superst
    0.14
    好运
    0.14
     ausp
    0.13
     astrolog
    0.12
     remedies
    0.12
     luck
    0.12
     unlucky
    0.12
     astrology
    0.11
     omen
    0.11
     rituals
    0.10
    Activations Density 0.044%

    No Known Activations