© 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. 21682
    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
     арқ
    -0.10
     any
    -0.08
     apparently
    -0.08
     feats
    -0.08
     credited
    -0.08
     dzięki
    -0.08
     flawlessly
    -0.08
     demonstrations
    -0.07
     unrhyw
    -0.07
    能够
    -0.07
    POSITIVE LOGITS
     warrants
    0.21
     warrant
    0.20
     بحاجة
    0.16
     investigate
    0.16
    需要
    0.15
     تحتاج
    0.15
    Needs
    0.15
     כדאי
    0.14
     Indicates
    0.14
     necessidade
    0.14
    Activations Density 0.038%

    No Known Activations