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. 113823
    Prev
    Next
    INDEX
    Explanations

    debt payments

    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
     दी
    -0.09
    金融
    -0.08
     bankers
    -0.08
    रिक
    -0.07
     accumulating
    -0.07
     की
    -0.07
     forfe
    -0.07
     spectrum
    -0.07
    福
    -0.07
     sifat
    -0.07
    POSITIVE LOGITS
     حضور
    0.09
    tä
    0.09
    iglio
    0.08
    zela
    0.08
     avance
    0.08
     nadal
    0.08
     liefst
    0.08
    дегі
    0.08
     Anmeldung
    0.08
     ребенка
    0.08
    Activations Density 0.006%

    No Known Activations