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. 9273
    Prev
    Next
    INDEX
    Explanations

    debt cancellation

    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
    ioni
    -0.08
    adina
    -0.07
    彦
    -0.07
     orches
    -0.07
              
    -0.07
     restaurantes
    -0.07
     اختر
    -0.07
    ्ख
    -0.07
    ിന്റ
    -0.07
     Young
    -0.07
    POSITIVE LOGITS
     dívida
    0.10
     Debt
    0.09
     debts
    0.09
     debt
    0.09
     aje
    0.08
    Debt
    0.08
     mercy
    0.08
     deuda
    0.08
     ineens
    0.08
     bankruptcy
    0.08
    Activations Density 0.009%

    No Known Activations