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. 54021
    Prev
    Next
    INDEX
    Explanations

    25

    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
     diplomatic
    -0.09
     negoc
    -0.09
     phạm
    -0.08
     Coordinates
    -0.08
     diplomacy
    -0.08
     financed
    -0.08
     اتخاذ
    -0.08
     Apprent
    -0.08
     deduction
    -0.08
     financement
    -0.08
    POSITIVE LOGITS
     fibra
    0.11
     wandelen
    0.10
     Dietary
    0.10
     fibras
    0.10
     dietary
    0.10
     diets
    0.10
     vegan
    0.09
     fiber
    0.09
     Fiber
    0.09
     ballast
    0.09
    Activations Density 0.009%

    No Known Activations