© 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. 96245
    Prev
    Next
    INDEX
    Explanations

    say "glass" or "cup"

    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
     voedsel
    -0.10
     food
    -0.10
     cozin
    -0.10
     cooks
    -0.10
     Cooking
    -0.09
     cooking
    -0.09
     خشک
    -0.09
     ഭക്ഷ
    -0.09
    Food
    -0.09
     Food
    -0.09
    POSITIVE LOGITS
     glass
    0.20
     glasses
    0.17
    glass
    0.16
     mug
    0.16
     Glass
    0.15
     cup
    0.15
    杯
    0.15
    Glass
    0.14
     gob
    0.14
     કપ
    0.14
    Activations Density 0.028%

    No Known Activations