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. 130768
    Prev
    Next
    INDEX
    Explanations

    sports technique

    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
     desafío
    -0.08
     Mardi
    -0.08
     Herausforderungen
    -0.08
    	query
    -0.08
    ascular
    -0.08
    ocale
    -0.08
    äß
    -0.08
     UObject
    -0.07
    给主人
    -0.07
     Sedan
    -0.07
    POSITIVE LOGITS
     launch
    0.12
     technique
    0.12
     mechanics
    0.12
     launches
    0.11
     release
    0.11
     timing
    0.11
    launch
    0.10
     técnica
    0.10
     Technique
    0.10
     power
    0.10
    Activations Density 0.031%

    No Known Activations