© 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. 21816
    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
     pareja
    -0.09
     знакомств
    -0.09
     alojamiento
    -0.09
    赁
    -0.08
    जन
    -0.08
     سری
    -0.08
     esposa
    -0.08
    Spline
    -0.08
    农村
    -0.08
    .serialize
    -0.08
    POSITIVE LOGITS
     uppercase
    0.25
     strtoupper
    0.22
    uppercase
    0.21
    -uppercase
    0.19
    .upper
    0.18
     ALL
    0.18
     CAPITAL
    0.16
     shouting
    0.16
    .BOLD
    0.16
    toupper
    0.16
    Activations Density 0.010%

    No Known Activations