© 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. 65502
    Prev
    Next
    INDEX
    Explanations

    collage

    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
    lie
    -0.08
     ingress
    -0.08
     Nissan
    -0.08
    iën
    -0.07
     liang
    -0.07
    lander
    -0.07
     Dear
    -0.07
     Tavern
    -0.07
     ارت
    -0.07
    sab
    -0.07
    POSITIVE LOGITS
     collage
    0.14
    制作
    0.11
     stitching
    0.09
     scrapbook
    0.09
    式
    0.09
    -making
    0.09
    -maker
    0.09
    orama
    0.09
    拼
    0.09
    写真
    0.08
    Activations Density 0.003%

    No Known Activations