© 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. 21832
    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
    -mêmes
    -0.08
    UMMY
    -0.08
    PELL
    -0.08
     bambini
    -0.08
    gebaut
    -0.08
     MONTH
    -0.08
     INST
    -0.08
    Upgrade
    -0.08
    IZED
    -0.08
    Employer
    -0.08
    POSITIVE LOGITS
     কেন্দ্র
    0.12
     ಕೇಂದ್ರ
    0.11
     perpendicular
    0.11
     intersection
    0.11
     axis
    0.11
     locus
    0.10
     центр
    0.10
     circle
    0.10
     center
    0.10
    circle
    0.10
    Activations Density 0.000%

    No Known Activations