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. 23-RESID-POST-AA
    6. 130921
    Prev
    Next
    INDEX
    Explanations

    say "module"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     president
    -0.09
     പ്രസിഡന്റ്
    -0.08
     राष्ट्रपति
    -0.08
     prezident
    -0.08
    ייסט
    -0.08
     అధ్యక్ష
    -0.08
     대통령
    -0.08
    -president
    -0.08
    总统
    -0.07
     Prezident
    -0.07
    POSITIVE LOGITS
     module
    0.74
    模块
    0.72
     módulo
    0.69
    _module
    0.68
     módulos
    0.68
    Module
    0.68
    module
    0.66
     Module
    0.66
    	module
    0.65
     modules
    0.64
    Activations Density 0.186%

    No Known Activations