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. 106243
    Prev
    Next
    INDEX
    Explanations

    verb "to be"

    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
    Seems
    -0.08
    leitung
    -0.08
    Hence
    -0.07
    Invest
    -0.07
    lah
    -0.07
    伏
    -0.07
     apres
    -0.07
    മ്പ
    -0.06
     sor
    -0.06
    -0.06
    POSITIVE LOGITS
    0.08
     Bobby
    0.08
     Bachelor
    0.08
     Aub
    0.08
    esion
    0.07
    .tint
    0.07
     Economist
    0.07
     Dunn
    0.07
    .es
    0.07
     SRC
    0.07
    Activations Density 0.135%

    No Known Activations