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. 98115
    Prev
    Next
    INDEX
    Explanations

    non-english / mod names

    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
    :NS
    -0.08
    :l
    -0.07
     sviluppo
    -0.07
     enje
    -0.07
     beber
    -0.07
     نتيجة
    -0.07
     asia
    -0.07
     HTTPS
    -0.07
     타입
    -0.07
    .types
    -0.07
    POSITIVE LOGITS
    translator
    0.08
    sub
    0.08
    _sub
    0.08
    locker
    0.08
    ెల
    0.08
    laagd
    0.08
    moving
    0.08
    ban
    0.08
     లో
    0.07
     impedit
    0.07
    Activations Density 0.001%

    No Known Activations