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. 15-RESID-POST-AA
    6. 29
    Prev
    Next
    INDEX
    Explanations

    Mathematical computations

    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
     {↵
    -0.08
    render
    -0.08
     koristiti
    -0.07
     NEW
    -0.07
     rende
    -0.07
    ':↵
    -0.07
     bruker
    -0.07
     {↵↵
    -0.07
     CURRENT
    -0.07
     render
    -0.07
    POSITIVE LOGITS
     apesar
    0.09
     again
    0.09
     있으
    0.09
     despite
    0.08
     bulun
    0.08
    こちら
    0.08
     unavoidable
    0.08
     awkward
    0.08
     zwar
    0.08
     unh
    0.08
    Activations Density 0.016%

    No Known Activations