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. 44084
    Prev
    Next
    INDEX
    Explanations

    справ

    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
    lod
    -0.09
    Hull
    -0.08
     Rud
    -0.08
     Hull
    -0.08
     Mol
    -0.07
     billet
    -0.07
    mol
    -0.07
     лод
    -0.07
    Mol
    -0.07
    Gil
    -0.07
    POSITIVE LOGITS
    ข
    0.08
     علاق
    0.08
     tale
    0.07
    ாற்ற
    0.07
    ীক
    0.07
     cheer
    0.07
    장
    0.07
     analogue
    0.07
    你好
    0.07
    ಾಂಕ
    0.07
    Activations Density 0.053%

    No Known Activations