© 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. 3-RESID-POST-AA
    11. 13321
    Prev
    Next
    INDEX
    Explanations

    температур

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    answers
    -0.07
     propose
    -0.07
     kak
    -0.07
     Kib
    -0.07
     kz
    -0.07
     Whitney
    -0.07
     underst
    -0.07
     healthcare
    -0.07
    Term
    -0.07
    じめ
    -0.07
    POSITIVE LOGITS
    טי
    0.08
    赛
    0.08
     Bür
    0.07
    删
    0.07
    傅
    0.07
    功
    0.07
    NA
    0.07
     注
    0.07
    毛
    0.07
     Corona
    0.07
    Activations Density 0.002%

    No Known Activations