© 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 EvalsExportsinterp-engineNEWAPI 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. 63183
    Prev
    Next
    INDEX
    Explanations

    direction choices

    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
    ayer
    -0.08
     defects
    -0.08
     कव
    -0.07
     geregeld
    -0.07
    िद्ध
    -0.07
    盗
    -0.07
     elf
    -0.07
     regelen
    -0.07
    phony
    -0.07
    clid
    -0.07
    POSITIVE LOGITS
    方向
    0.18
     방향
    0.18
     direction
    0.17
     Richtung
    0.17
     direção
    0.16
     arah
    0.16
     दिशा
    0.16
    _direction
    0.16
     напрям
    0.15
     نحو
    0.15
    Activations Density 0.073%

    No Known Activations