© 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. 112423
    Prev
    Next
    INDEX
    Explanations

    food nutritional content

    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
     permutations
    -0.09
     дет
    -0.09
     cleaners
    -0.08
     игроков
    -0.08
     panjang
    -0.08
    players
    -0.08
    excluded
    -0.08
     bidders
    -0.08
    ял
    -0.08
     exclusions
    -0.08
    POSITIVE LOGITS
     efficacy
    0.09
     owing
    0.08
     Alcal
    0.08
     extrac
    0.08
     eficacia
    0.07
     ngenxa
    0.07
    oplast
    0.07
     eficácia
    0.07
     effectiveness
    0.07
     díky
    0.07
    Activations Density 0.008%

    No Known Activations