© 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. 96643
    Prev
    Next
    INDEX
    Explanations

    grains

    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
     alcoholism
    -0.12
     jabón
    -0.09
     Erotik
    -0.09
    การพนัน
    -0.09
     Alkohol
    -0.09
    委员会
    -0.08
     Glücksspiel
    -0.08
    ixing
    -0.08
    福利彩票
    -0.08
     Alcohol
    -0.08
    POSITIVE LOGITS
     quinoa
    0.31
     rice
    0.19
     arroz
    0.18
     brown
    0.17
    Qu
    0.16
     grains
    0.16
     cous
    0.16
     pasta
    0.16
     noodles
    0.15
     Qu
    0.15
    Activations Density 0.043%

    No Known Activations