© 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. 11-RESID-POST-AA
    11. 77972
    Prev
    Next
    INDEX
    Explanations

    Numbers and quantities

    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
    .coords
    -0.09
     crossing
    -0.09
     marijuana
    -0.09
     kcal
    -0.08
    adb
    -0.08
     Crossing
    -0.08
     metabolites
    -0.08
     metabol
    -0.08
     FBI
    -0.07
     uyu
    -0.07
    POSITIVE LOGITS
     എണ്ണം
    0.11
    _batches
    0.09
     Plates
    0.09
    OUNDS
    0.09
     plates
    0.09
     Seasons
    0.09
     Anzahl
    0.09
    .Number
    0.09
    数量
    0.08
    Количество
    0.08
    Activations Density 0.051%

    No Known Activations