© 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. 21169
    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
    iest
    -0.09
    ularity
    -0.09
    开始
    -0.08
    icial
    -0.08
     começo
    -0.08
     start
    -0.08
     início
    -0.08
    什么时候
    -0.08
    ivan
    -0.08
     Beginn
    -0.08
    POSITIVE LOGITS
     with
    0.16
     áfram
    0.15
     עם
    0.14
     to
    0.14
     הלא
    0.13
     unab
    0.13
     tục
    0.13
     exploring
    0.13
     indefinitely
    0.13
     với
    0.13
    Activations Density 0.025%

    No Known Activations