© 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. 97726
    Prev
    Next
    INDEX
    Explanations

    say "store" word

    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
     الفكر
    -0.08
     theolog
    -0.07
    ాభ
    -0.07
     epistem
    -0.07
     trenches
    -0.07
     décro
    -0.07
     перспектив
    -0.07
     pertin
    -0.07
     Orwell
    -0.07
     eldest
    -0.07
    POSITIVE LOGITS
     store
    0.27
     магазин
    0.26
     দোক
    0.25
     магазине
    0.25
     commercially
    0.24
     tienda
    0.24
     purchased
    0.23
    store
    0.23
     магазина
    0.23
     supermarket
    0.23
    Activations Density 0.098%

    No Known Activations