Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56059
    Prev
    Next
    INDEX
    Explanations

    shut

    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
    .stroke
    -0.08
     Tattoo
    -0.08
     stre
    -0.08
     걸
    -0.08
    uvian
    -0.08
    724
    -0.08
     tattoos
    -0.08
     BU
    -0.07
    BU
    -0.07
     tattoo
    -0.07
    POSITIVE LOGITS
    截
    0.08
     hog
    0.08
     spur
    0.07
    候
    0.07
     shut
    0.07
    いた
    0.07
    令
    0.07
    烈
    0.07
     poj
    0.07
     components
    0.07
    Activations Density 0.005%

    No Known Activations