© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 97745
    Prev
    Next
    INDEX
    Explanations

    say "pork"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    菠菜
    -0.09
    证券
    -0.09
     ome
    -0.09
     emerald
    -0.08
     securities
    -0.08
     convol
    -0.08
     rodada
    -0.08
     subst
    -0.08
     sauté
    -0.08
     lance
    -0.08
    POSITIVE LOGITS
     pulled
    0.16
     ribs
    0.14
     Pul
    0.13
    Pul
    0.12
    pul
    0.11
     BBQ
    0.11
     पुल
    0.11
    Бар
    0.11
     bar
    0.10
     BAR
    0.10
    Activations Density 0.016%

    No Known Activations