© 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. 7986
    Prev
    Next
    INDEX
    Explanations

    interpreting user intent

    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
     вполне
    -0.08
     Employ
    -0.08
     Classic
    -0.08
     Concert
    -0.08
     wedd
    -0.08
     ganske
    -0.08
     Partner
    -0.08
     lh
    -0.08
     classique
    -0.08
    nal
    -0.08
    POSITIVE LOGITS
    たり
    0.09
    ?"
    0.08
    」、「
    0.08
    とか
    0.08
    Chapter
    0.08
    하거나
    0.08
    」「
    0.08
    EZ
    0.08
    有哪些
    0.07
     troubleshoot
    0.07
    Activations Density 0.129%

    No Known Activations