© 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. 22587
    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
     television
    -0.09
     sogenannten
    -0.09
     Российской
    -0.08
     televisão
    -0.08
     собственной
    -0.08
     Corporation
    -0.08
     sogen
    -0.08
     sogenannte
    -0.08
     České
    -0.08
     governmental
    -0.08
    POSITIVE LOGITS
     veggies
    0.12
    ,etc
    0.10
     carbs
    0.10
    ,..
    0.10
     &:
    0.10
    =>
    0.10
     meds
    0.10
    ,色
    0.10
     соц
    0.09
     it's
    0.09
    Activations Density 0.115%

    No Known Activations