© 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. 103481
    Prev
    Next
    INDEX
    Explanations

    numerical computations

    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
    ane
    -0.11
    않
    -0.09
    afanya
    -0.08
     artístico
    -0.08
    awon
    -0.08
    ੈਂ
    -0.08
     અથવા
    -0.08
     föl
    -0.08
    amá
    -0.08
    .product
    -0.08
    POSITIVE LOGITS
    993
    0.09
     المرحلة
    0.09
     domic
    0.08
    வரி
    0.08
     الدخول
    0.08
     საც
    0.08
    154
    0.08
    982
    0.08
    934
    0.08
    991
    0.08
    Activations Density 0.061%

    No Known Activations