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. 65056
    Prev
    Next
    INDEX
    Explanations

    founded

    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
    Wildcard
    -0.08
     Kub
    -0.08
     domác
    -0.08
    iyalar
    -0.08
    Kub
    -0.07
    wild
    -0.07
    Uy
    -0.07
     wild
    -0.07
    Kul
    -0.07
     tomography
    -0.07
    POSITIVE LOGITS
     founding
    0.15
     founded
    0.13
     Founded
    0.12
     gegründet
    0.11
     تأس
    0.11
    Founded
    0.11
     founders
    0.11
     inception
    0.11
     opgericht
    0.11
     байгуу
    0.11
    Activations Density 0.091%

    No Known Activations