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. 76287
    Prev
    Next
    INDEX
    Explanations

    volume

    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
     coke
    -0.08
    Spect
    -0.08
     Residents
    -0.08
    TECT
    -0.08
     porcelain
    -0.08
     coloration
    -0.08
    ICI
    -0.08
     roar
    -0.08
    _PIX
    -0.08
     shades
    -0.08
    POSITIVE LOGITS
     pedido
    0.08
    title
    0.08
    ediakan
    0.08
    切
    0.08
     origen
    0.07
    ֵ
    0.07
     заказа
    0.07
     tato
    0.07
    /button
    0.07
    订单
    0.07
    Activations Density 0.000%

    No Known Activations