© 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. 21704
    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
     chooses
    -0.09
     влияет
    -0.08
     knows
    -0.08
    boss
    -0.08
     marrying
    -0.08
    cruit
    -0.08
    겁
    -0.08
     altering
    -0.08
    verters
    -0.08
     taxes
    -0.08
    POSITIVE LOGITS
     placed
    0.15
     placé
    0.13
     place
    0.12
     Place
    0.12
    placed
    0.12
     placing
    0.12
     Placement
    0.12
     placement
    0.11
    Placed
    0.11
     plass
    0.11
    Activations Density 0.003%

    No Known Activations