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. 98621
    Prev
    Next
    INDEX
    Explanations

    Preg

    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
     zale
    -0.08
    ized
    -0.08
     prve
    -0.07
    veys
    -0.07
    cke
    -0.07
     bei
    -0.07
    алов
    -0.07
     o
    -0.07
    -0.07
    изи
    -0.07
    POSITIVE LOGITS
    untas
    0.25
    unta
    0.21
    unt
    0.17
    untar
    0.17
    nancy
    0.16
    unte
    0.16
    unto
    0.15
    ú
    0.15
    nant
    0.14
    UNT
    0.14
    Activations Density 0.001%

    No Known Activations