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. 108956
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    Fare
    -0.08
     fare
    -0.08
     করেছি
    -0.07
     př
    -0.07
     shingles
    -0.07
    ملت
    -0.07
    مراء
    -0.07
     fueling
    -0.07
     NAD
    -0.07
     boosting
    -0.07
    POSITIVE LOGITS
    側
    0.08
     CON
    0.07
     Techn
    0.07
     Specialist
    0.07
    Operator
    0.07
     tecnico
    0.07
    gericht
    0.07
    似
    0.07
    daemon
    0.07
    -Team
    0.07
    Activations Density 0.205%

    No Known Activations