© 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. 23-RESID-POST-AA
    11. 51104
    Prev
    Next
    INDEX
    Explanations

    Cantonese phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roads
    -0.09
    angé
    -0.09
    werke
    -0.08
    -write
    -0.08
     salute
    -0.08
     Werk
    -0.08
     pieza
    -0.08
     peça
    -0.08
     soldi
    -0.08
    -workers
    -0.08
    POSITIVE LOGITS
     maan
    0.09
    aat
    0.08
     naap
    0.08
    Sum
    0.08
    Caption
    0.08
    ngor
    0.08
    NG
    0.08
     captions
    0.08
    3
    0.07
    _sum
    0.07
    Activations Density 0.001%

    No Known Activations