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. 7-RESID-POST-AA
    6. 130986
    Prev
    Next
    INDEX
    Explanations

    United

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aison
    -0.10
    mi
    -0.08
    .Na
    -0.08
    urit
    -0.07
    úl
    -0.07
    loan
    -0.07
     تو
    -0.07
    di
    -0.07
    青
    -0.07
     Maya
    -0.07
    POSITIVE LOGITS
     İstanbul
    0.08
     chore
    0.08
    Aware
    0.07
    起来
    0.07
     Portugal
    0.07
     cortical
    0.07
     Ahmedabad
    0.07
    но
    0.07
     শুধু
    0.07
     москов
    0.07
    Activations Density 0.006%

    No Known Activations