© 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. 22623
    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
     Details
    -0.08
     Insights
    -0.08
     parâ
    -0.08
     फायदा
    -0.08
     comentario
    -0.07
     Insight
    -0.07
    promo
    -0.07
     requisito
    -0.07
     parametro
    -0.07
     favorites
    -0.07
    POSITIVE LOGITS
     overarching
    0.17
     overall
    0.16
     pangunahing
    0.16
     haupts
    0.16
     inherent
    0.16
     основные
    0.16
     أبرز
    0.16
     հիմնական
    0.15
    总体
    0.15
     основных
    0.15
    Activations Density 0.082%

    No Known Activations