© 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. 47840
    Prev
    Next
    INDEX
    Explanations

    ól/pól

    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
    ielsweise
    -0.07
     Schaden
    -0.07
     molt
    -0.07
    луата
    -0.07
     ई
    -0.07
     EL
    -0.07
     তাল
    -0.07
    .if
    -0.07
     bilm
    -0.07
    supported
    -0.07
    POSITIVE LOGITS
    vora
    0.10
     suspicious
    0.09
    iza
    0.09
     suspe
    0.08
    izas
    0.08
    989
    0.08
    ニー
    0.08
     dangerous
    0.08
     advent
    0.07
    ulated
    0.07
    Activations Density 0.000%

    No Known Activations