© 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. 70079
    Prev
    Next
    INDEX
    Explanations

    chess pawn movement

    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
     modules
    -0.08
    ીઓ
    -0.08
     contraintes
    -0.08
     chiến
    -0.08
    Neighbour
    -0.08
     neighbors
    -0.08
     Modules
    -0.08
     métro
    -0.08
     neighbor
    -0.08
    Neighbors
    -0.08
    POSITIVE LOGITS
     membawa
    0.08
    倍
    0.08
    reichen
    0.08
    _sheet
    0.07
     traumatic
    0.07
     zve
    0.07
     GIVE
    0.07
     curved
    0.07
     गर्�
    0.07
     қызмет
    0.07
    Activations Density 0.002%

    No Known Activations