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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48109
    Prev
    Next
    INDEX
    Explanations

    say "sweet"

    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
     lung
    -0.11
     pulm
    -0.10
     Lung
    -0.10
     폐
    -0.10
     lungs
    -0.10
     pelvis
    -0.10
     NRA
    -0.10
     thor
    -0.10
     stadium
    -0.10
     atmospheric
    -0.10
    POSITIVE LOGITS
     sweetness
    0.56
    甜
    0.52
     sweet
    0.52
     sugar
    0.51
     слад
    0.50
     sweets
    0.50
     sugary
    0.50
     Sweet
    0.49
    Sweet
    0.49
    糖
    0.48
    Activations Density 0.188%

    No Known Activations