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. 106293
    Prev
    Next
    INDEX
    Explanations

    Euclidean Algorithm calculations

    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
    -rays
    -0.08
    -energy
    -0.08
    原则
    -0.08
    -green
    -0.08
    -paying
    -0.08
     principios
    -0.08
    -three
    -0.08
     Rela
    -0.08
    -wa
    -0.08
     welded
    -0.08
    POSITIVE LOGITS
    ask
    0.07
    ют
    0.07
    0.07
    Ob
    0.07
    ieno
    0.07
     ask
    0.07
     य
    0.07
     idioma
    0.07
     zor
    0.07
     з
    0.07
    Activations Density 0.013%

    No Known Activations