© 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. 19476
    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
     is
    -0.10
     has
    -0.10
     سجل
    -0.08
     є
    -0.08
     cujo
    -0.08
     was
    -0.08
    whose
    -0.08
    자인
    -0.08
     cuyo
    -0.07
     является
    -0.07
    POSITIVE LOGITS
     περίπου
    0.17
     Approximately
    0.17
     около
    0.16
     umbes
    0.16
     approximately
    0.16
     ongeveer
    0.15
     حوالي
    0.15
     ಸುಮಾರು
    0.15
    approximately
    0.15
    Approximately
    0.15
    Activations Density 0.023%

    No Known Activations