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

    Neuronpedia

    APICircuit 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. 11966
    Prev
    Next
    INDEX
    Explanations

    quotes

    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
    adin
    -0.07
    esto
    -0.07
     invasive
    -0.07
    ০০
    -0.07
    thead
    -0.07
     Maryland
    -0.07
     indicate
    -0.07
    ()(
    -0.07
    aito
    -0.07
     fid
    -0.07
    POSITIVE LOGITS
    .myapplication
    0.09
     পৃথিব
    0.09
     tapestry
    0.08
     omkring
    0.08
     kale
    0.08
     мире
    0.08
     ప్రపంచ
    0.08
     verändern
    0.08
     लोकत
    0.08
     explotación
    0.08
    Activations Density 0.059%

    No Known Activations