© 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. 51391
    Prev
    Next
    INDEX
    Explanations

    genetics

    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
     paddle
    -0.12
     merchant
    -0.11
     Paddle
    -0.11
     cups
    -0.11
     scooter
    -0.10
     المسجد
    -0.10
     horeca
    -0.10
    杯
    -0.10
     кафе
    -0.10
     mosque
    -0.10
    POSITIVE LOGITS
     genetic
    0.61
     Genetic
    0.55
     genetics
    0.54
     genética
    0.53
     gene
    0.52
     genet
    0.52
     genes
    0.52
     Genetics
    0.49
    _gene
    0.49
     genotype
    0.48
    Activations Density 0.154%

    No Known Activations