© 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. 44607
    Prev
    Next
    INDEX
    Explanations

    Apologies for not attending

    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
     корруп
    -0.09
     மே
    -0.08
     Assign
    -0.08
     gedeelte
    -0.08
     Text
    -0.07
    诈
    -0.07
     חוק
    -0.07
     assigning
    -0.07
     yaş
    -0.07
     zwi
    -0.07
    POSITIVE LOGITS
    TA
    0.09
    joined
    0.08
    下午
    0.08
    ಿಕೊಂಡ
    0.08
     försö
    0.08
    आज
    0.08
    هوم
    0.08
    ridden
    0.08
    attered
    0.07
    /gallery
    0.07
    Activations Density 0.028%

    No Known Activations