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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19418
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ,Moda
    -0.16
    <|endofprompt|>
    -0.16
     вуҷ
    -0.16
    ҟәатәи
    -0.16
    夫妻性生活影片
    -0.16
     тәләп
    -0.16
    ҵит
    -0.16
    ьыр
    -0.16
    -0.16
    әнди
    -0.16
    POSITIVE LOGITS
     hours
    0.13
     million
    0.12
     seconds
    0.12
     days
    0.11
     kg
    0.11
     km
    0.11
     liters
    0.11
    °C
    0.11
     minutes
    0.11
     weeks
    0.11
    Activations Density 0.113%
    No Known Activations