© 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. 18522
    Prev
    Next
    INDEX
    Explanations

    Foreign time words

    np_max-act-logits · gemini-2.0-flash
    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
    .not
    -0.08
     Breakdown
    -0.07
     ends
    -0.07
    .any
    -0.07
    .one
    -0.07
     occurs
    -0.07
     revanche
    -0.07
    .discovery
    -0.07
     sería
    -0.07
     ഒരു
    -0.07
    POSITIVE LOGITS
     منذ
    0.23
    以来
    0.23
     sejak
    0.22
     bisherigen
    0.21
     lately
    0.20
     અત્યાર
    0.20
     bisher
    0.20
    Depuis
    0.20
     Depuis
    0.20
    一直
    0.20
    Activations Density 0.336%

    No Known Activations