© 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. 21310
    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
    [N
    -0.08
    .ce
    -0.08
    -0.08
     ([
    -0.08
    "[
    -0.08
    чным
    -0.08
    [X
    -0.08
    [i
    -0.08
     बजाय
    -0.08
    [mid
    -0.08
    POSITIVE LOGITS
     overhead
    0.13
     taxes
    0.10
     leið
    0.10
     impuestos
    0.09
     учета
    0.09
     furnishings
    0.09
     boiler
    0.09
     garnish
    0.09
     negligible
    0.09
     placeholders
    0.09
    Activations Density 0.022%
    No Known Activations