© 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. 21200
    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
    ,
    -0.10
     positive
    -0.09
    .↵↵
    -0.09
     (
    -0.09
    Positive
    -0.09
     Positive
    -0.09
    .
    -0.08
     global
    -0.08
    /
    -0.08
     positivity
    -0.08
    POSITIVE LOGITS
     exactly
    0.19
     exatamente
    0.19
     slightly
    0.18
     exactement
    0.17
     exactamente
    0.17
     precisely
    0.16
     exakt
    0.15
     בדיוק
    0.15
     EXACT
    0.15
     precies
    0.15
    Activations Density 0.036%

    No Known Activations