© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 96332
    Prev
    Next
    INDEX
    Explanations

    body composition measurements

    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
     authoritarian
    -0.10
     давление
    -0.09
    壮
    -0.09
     communist
    -0.08
    市委
    -0.08
     причиной
    -0.08
     марказ
    -0.08
    да
    -0.08
     давления
    -0.07
     сиё
    -0.07
    POSITIVE LOGITS
    .Skip
    0.09
    zky
    0.09
     skins
    0.09
    affen
    0.08
     Dual
    0.08
     dual
    0.08
     Navy
    0.08
     skin
    0.08
    sk
    0.08
    zki
    0.08
    Activations Density 0.000%

    No Known Activations