Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 43600
    Prev
    Next
    INDEX
    Explanations

    WAN

    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
     박
    -0.09
     eigen
    -0.09
     körper
    -0.09
     موسی
    -0.08
     utens
    -0.08
     juguetes
    -0.08
     jur
    -0.08
     مسلمان
    -0.08
     silence
    -0.08
     plonge
    -0.07
    POSITIVE LOGITS
     WAN
    0.10
    WAN
    0.09
    CRM
    0.09
    Remote
    0.08
    (remote
    0.08
    -google
    0.08
    kms
    0.08
    cmp
    0.08
    oq
    0.08
     intelligently
    0.08
    Activations Density 0.004%

    No Known Activations