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. 78095
    Prev
    Next
    INDEX
    Explanations

    end

    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
     Act
    -0.08
    ље
    -0.08
    ие
    -0.08
     новом
    -0.08
     пир
    -0.08
     الإيراني
    -0.07
    Act
    -0.07
     allez
    -0.07
     похуд
    -0.07
    ',{
    -0.07
    POSITIVE LOGITS
    基金
    0.09
    ūra
    0.09
    Sistema
    0.08
    ラム
    0.08
    DAO
    0.08
    Seeds
    0.08
    Funds
    0.08
     funds
    0.08
     botanical
    0.08
     財
    0.08
    Activations Density 0.008%

    No Known Activations