© 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. 22676
    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
     accrued
    -0.07
     Formatting
    -0.07
     напряж
    -0.07
    Formatting
    -0.07
     vink
    -0.07
     inzicht
    -0.07
     accru
    -0.07
    น้ำ
    -0.07
    _scroll
    -0.07
    Insets
    -0.07
    POSITIVE LOGITS
     replacement
    0.52
     replacing
    0.50
     replacements
    0.50
     reempl
    0.49
     remplacement
    0.49
     Replacement
    0.49
     remplacer
    0.49
    替
    0.48
    Replacement
    0.48
     replace
    0.48
    Activations Density 0.136%

    No Known Activations