© 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 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. 21226
    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
     somebody
    -0.16
    because
    -0.16
    the
    -0.15
    really
    -0.13
     basically
    -0.13
    whatever
    -0.13
    等等
    -0.13
    的时候
    -0.13
     everybody
    -0.13
     things
    -0.13
    POSITIVE LOGITS
    0.12
    ’র
    0.11
     უზრუნველ
    0.11
    0.11
     განვით
    0.11
     վաղ
    0.11
     საუკეთ
    0.11
     福利彩票天天彩
    0.11
    ussutiss
    0.11
    তুন
    0.11
    Activations Density 0.431%
    No Known Activations