© 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. 19707
    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
     stuff
    -0.08
     fights
    -0.08
     glimps
    -0.08
     partially
    -0.07
     would
    -0.07
     uses
    -0.07
     can
    -0.07
     others
    -0.07
     birçok
    -0.07
     removed
    -0.07
    POSITIVE LOGITS
     spätestens
    0.21
     موعد
    0.15
    期限
    0.14
     uiterlijk
    0.13
     deadline
    0.13
     plazo
    0.13
     stipulated
    0.12
     preferably
    0.12
     entro
    0.12
     сроки
    0.12
    Activations Density 0.036%

    No Known Activations