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. 35
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     certain
    -0.09
     некоторых
    -0.09
    某
    -0.08
    Hindi
    -0.08
     some
    -0.08
     ụfọdụ
    -0.08
     or
    -0.08
    രുമ
    -0.08
    ល
    -0.08
     qaar
    -0.08
    POSITIVE LOGITS
    conversion
    0.08
    certe
    0.08
     protože
    0.07
    press
    0.07
     bygg
    0.07
     asci
    0.07
     bygger
    0.07
    bella
    0.07
     dejando
    0.07
    avos
    0.07
    Activations Density 0.111%

    No Known Activations