© 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. 19-RESID-POST-AA
    11. 103252
    Prev
    Next
    INDEX
    Explanations

    Drug

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    рш
    -0.09
    hnte
    -0.08
     sûrement
    -0.08
    Grouped
    -0.08
    ாள்
    -0.08
     консульта
    -0.08
    KT
    -0.08
    BA
    -0.08
    WW
    -0.08
    WK
    -0.08
    POSITIVE LOGITS
    ging
    0.14
    ged
    0.14
    gable
    0.13
    store
    0.12
    gings
    0.12
    smith
    0.11
    bery
    0.11
    bing
    0.11
    ovima
    0.10
    worthiness
    0.10
    Activations Density 0.008%

    No Known Activations