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. 65093
    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
    unächst
    -0.08
    且
    -0.08
     hipó
    -0.08
    بق
    -0.08
    abez
    -0.08
    理念
    -0.08
    那些
    -0.08
    ্যের
    -0.08
     Street
    -0.07
     sério
    -0.07
    POSITIVE LOGITS
     usw
    0.08
     inconvenient
    0.08
     Можно
    0.08
    Друг
    0.08
    Notation
    0.08
    Можно
    0.08
     표현
    0.08
    Savings
    0.08
     notation
    0.08
    ograms
    0.08
    Activations Density 0.032%

    No Known Activations