© 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 EvalsExportsAPI 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. 21221
    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
     both
    -0.10
     Atu
    -0.08
     only
    -0.08
     خودش
    -0.07
     kolm
    -0.07
     vergro
    -0.07
     headlights
    -0.07
     edge
    -0.07
     energy
    -0.07
     Atlant
    -0.07
    POSITIVE LOGITS
     आदि
    0.19
     વગેરે
    0.18
    など
    0.16
     등의
    0.16
     וכו
    0.16
    ,etc
    0.15
     etc
    0.15
    ,...
    0.14
     وغيرها
    0.14
    ”等
    0.14
    Activations Density 0.001%

    No Known Activations