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. 111772
    Prev
    Next
    INDEX
    Explanations

    shop

    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
    Netflix
    -0.09
     snork
    -0.08
     Cozy
    -0.08
     тус
    -0.08
     Goodreads
    -0.08
     yearning
    -0.08
     concept
    -0.08
     recop
    -0.08
     Netflix
    -0.08
     chemo
    -0.07
    POSITIVE LOGITS
    出售
    0.10
    .sell
    0.09
     trader
    0.09
     disputes
    0.09
    .invoice
    0.09
     craftsmen
    0.09
     verkauft
    0.09
     ruler
    0.08
     البيع
    0.08
     doubtful
    0.08
    Activations Density 0.026%

    No Known Activations