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. 54113
    Prev
    Next
    INDEX
    Explanations

    multiplication

    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
     burner
    -0.08
    Ru
    -0.08
     Ruiz
    -0.08
     indifferent
    -0.08
     antagonist
    -0.08
     прибор
    -0.07
    Reject
    -0.07
    -0.07
     thuốc
    -0.07
    त
    -0.07
    POSITIVE LOGITS
     suure
    0.09
     પૈ
    0.09
    乘
    0.09
     বিজ
    0.09
     əmək
    0.08
    -business
    0.08
     mei
    0.08
     Она
    0.08
     Turbo
    0.08
     multiplying
    0.08
    Activations Density 0.035%

    No Known Activations