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. 106313
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    128
    -0.09
     jig
    -0.08
     लग
    -0.08
     undec
    -0.08
    麻
    -0.08
    lob
    -0.07
    -as
    -0.07
     тик
    -0.07
     united
    -0.07
     Victor
    -0.07
    POSITIVE LOGITS
     electronically
    0.08
     Kosov
    0.08
    äischen
    0.07
     Grau
    0.07
     നിന്നും
    0.07
     Tiene
    0.07
    銀行
    0.07
    BANK
    0.07
     steuer
    0.07
     Workspace
    0.07
    Activations Density 0.003%

    No Known Activations