© 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. 21303
    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
    irmos
    -0.08
     remained
    -0.08
    도가
    -0.08
    -0.08
     толщ
    -0.08
     lutter
    -0.07
     ಇದ್ದ
    -0.07
     adequ
    -0.07
    .remaining
    -0.07
    remaining
    -0.07
    POSITIVE LOGITS
     manipulating
    0.17
     sabot
    0.17
     misleading
    0.17
     exploiting
    0.17
     manipulate
    0.16
     cunning
    0.16
     manipulated
    0.16
    Manip
    0.16
     manip
    0.16
     manipulation
    0.16
    Activations Density 0.068%
    No Known Activations