© 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. 45489
    Prev
    Next
    INDEX
    Explanations

    starting or ending conversation

    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
     Somos
    -0.08
    rosis
    -0.08
     Nuclear
    -0.08
     spokesman
    -0.08
     শব্দ
    -0.08
     CONTROL
    -0.08
    -0.08
     Philosophy
    -0.07
     Minas
    -0.07
    zano
    -0.07
    POSITIVE LOGITS
     gespannt
    0.12
    を見る
    0.10
     görmek
    0.10
    看到
    0.10
     benieuwd
    0.09
     vedere
    0.09
     veure
    0.09
     watching
    0.09
     kuona
    0.09
    /watch
    0.09
    Activations Density 0.089%
    No Known Activations