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. 15-RESID-POST-AA
    6. 19337
    Prev
    Next
    INDEX
    Explanations

    Comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     National
    -0.08
     করবেন
    -0.08
     William
    -0.08
     בן
    -0.07
     �
    -0.07
    eneo
    -0.07
    'es
    -0.07
     Claim
    -0.07
     Archives
    -0.07
     զ
    -0.07
    POSITIVE LOGITS
    elp
    0.09
    测试
    0.08
    Weighted
    0.08
    ীদের
    0.08
     polarized
    0.08
    _c
    0.08
    训练
    0.08
    crypted
    0.08
     minced
    0.08
    hashed
    0.08
    Activations Density 0.003%

    No Known Activations