© 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. 11-RESID-POST-AA
    11. 79185
    Prev
    Next
    INDEX
    Explanations

    between

    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
    大片
    -0.07
    ॉ
    -0.07
    ई
    -0.07
    ेम
    -0.07
    mis
    -0.07
     jig
    -0.07
     circulate
    -0.07
    tep
    -0.06
    leté
    -0.06
     độc
    -0.06
    POSITIVE LOGITS
    죄
    0.09
     �
    0.08
     pokuš
    0.08
     möglichst
    0.08
     heet
    0.08
     너
    0.08
     ejac
    0.08
     получилось
    0.08
    .Н
    0.08
     Таким
    0.07
    Activations Density 0.620%

    No Known Activations