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. 11-RESID-POST-AA
    6. 88322
    Prev
    Next
    INDEX
    Explanations

    divisors and factors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myself
    -0.08
     nurse
    -0.08
     Myself
    -0.08
     ten
    -0.07
     nurses
    -0.07
     charger
    -0.07
     navigator
    -0.07
     Maxwell
    -0.07
     Masters
    -0.07
     ouvrir
    -0.07
    POSITIVE LOGITS
    �
    0.08
    Воз
    0.08
     allegiance
    0.08
    "http
    0.08
    ixi
    0.08
     Atlético
    0.08
    FLT
    0.08
     dietary
    0.08
    Cached
    0.07
    'iz
    0.07
    Activations Density 0.016%

    No Known Activations