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. 60803
    Prev
    Next
    INDEX
    Explanations

    form

    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
     Untersuch
    -0.09
     publ
    -0.09
    ിരുന്ന
    -0.09
     nodig
    -0.08
    optimal
    -0.08
    薦
    -0.08
    pụ
    -0.08
    LN
    -0.08
     Gradient
    -0.08
     limestone
    -0.07
    POSITIVE LOGITS
     أنحاء
    0.08
     forum
    0.08
     faithfully
    0.08
     Az
    0.08
    ګه
    0.08
     prejud
    0.07
     trademarks
    0.07
     whatsoever
    0.07
    மாக
    0.07
     transpl
    0.07
    Activations Density 0.001%

    No Known Activations