© 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. 20302
    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
    $.
    -0.08
     sabot
    -0.08
    istor
    -0.08
     #
    -0.08
     Z
    -0.08
    ^-
    -0.07
    #
    -0.07
    .js
    -0.07
    ocations
    -0.07
     Tantra
    -0.07
    POSITIVE LOGITS
     shalt
    0.14
     unto
    0.12
     hath
    0.12
     ибо
    0.11
     Plaintiff
    0.10
     “…
    0.10
     shall
    0.10
     thou
    0.10
     MERCHANTABILITY
    0.10
     harum
    0.09
    Activations Density 0.011%

    No Known Activations