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. 97977
    Prev
    Next
    INDEX
    Explanations

    factorizations of 2005/2015

    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
    KB
    -0.08
    857
    -0.08
    ν
    -0.08
    νώ
    -0.08
     quotient
    -0.08
    QT
    -0.08
     Wright
    -0.07
    912
    -0.07
    AU
    -0.07
    Won
    -0.07
    POSITIVE LOGITS
    erezh
    0.09
    -ш
    0.09
     divorced
    0.08
    ический
    0.08
     лиц
    0.08
    -п
    0.08
     licence
    0.08
     Александр
    0.08
     ċ
    0.08
     aly
    0.08
    Activations Density 0.002%

    No Known Activations