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. 119353
    Prev
    Next
    INDEX
    Explanations

    cloud

    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
     Shopping
    -0.08
     shopping
    -0.08
     Kindergarten
    -0.07
     concussion
    -0.07
     bagu
    -0.07
    טרה
    -0.07
     Wizard
    -0.07
     Dentist
    -0.07
    ینه
    -0.07
    ترل
    -0.07
    POSITIVE LOGITS
    'aj
    0.08
     generous
    0.08
     großzüg
    0.08
     গো
    0.07
     alluring
    0.07
    -Ind
    0.07
    ുട
    0.07
    됨
    0.07
    些什么
    0.07
     लौट
    0.07
    Activations Density 0.003%

    No Known Activations