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. 12993
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    တွေ
    -0.08
     Drap
    -0.08
    kens
    -0.07
     Classic
    -0.07
     лег
    -0.07
     Hammond
    -0.07
    였
    -0.07
     Splash
    -0.07
     matér
    -0.07
    imming
    -0.07
    POSITIVE LOGITS
     abril
    0.09
     trae
    0.08
     enviado
    0.08
    -sol
    0.08
     comparable
    0.08
    Px
    0.08
     నగ
    0.08
     blader
    0.07
     especie
    0.07
     vergel
    0.07
    Activations Density 0.056%

    No Known Activations