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. 23564
    Prev
    Next
    INDEX
    Explanations

    key

    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
     شام
    -0.08
     Serbian
    -0.08
     שבע
    -0.08
     alem
    -0.08
     Electric
    -0.07
     borrowing
    -0.07
     του
    -0.07
     Gail
    -0.07
     Petro
    -0.07
     Vigil
    -0.07
    POSITIVE LOGITS
    kter
    0.08
     ausz
    0.08
    คะแนน
    0.08
     acties
    0.08
    ลูก
    0.08
     nominated
    0.08
     actionable
    0.07
     usando
    0.07
    Business
    0.07
    ตาม
    0.07
    Activations Density 0.003%

    No Known Activations