© 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. 21702
    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
     Watching
    -0.10
     ();↵↵
    -0.09
     Something
    -0.09
     něco
    -0.09
    something
    -0.09
     Functions
    -0.09
     ();
    -0.09
     Somehow
    -0.09
    Broken
    -0.08
     Paths
    -0.08
    POSITIVE LOGITS
    基本
    0.08
    élite
    0.08
     الأساسية
    0.08
    主要
    0.08
    标准
    0.07
     تدخل
    0.07
     administrative
    0.07
     были
    0.07
    ，此
    0.07
     були
    0.07
    Activations Density 0.001%

    No Known Activations