© 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. 11-RESID-POST-AA
    11. 91324
    Prev
    Next
    INDEX
    Explanations

    sexually transmitted infections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     legendary
    -0.08
     стор
    -0.08
    성이
    -0.07
     showing
    -0.07
     constructing
    -0.07
    성을
    -0.07
     golfing
    -0.07
    thinking
    -0.07
     여
    -0.07
     tá
    -0.07
    POSITIVE LOGITS
     pollutants
    0.08
    在线视频
    0.08
     cleansing
    0.08
     Rail
    0.08
     acompañ
    0.08
    交换
    0.08
     IOException
    0.07
     Nal
    0.07
     mmol
    0.07
    在线观看
    0.07
    Activations Density 0.002%

    No Known Activations