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. 59840
    Prev
    Next
    INDEX
    Explanations

    2

    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
     dirige
    -0.08
    Г
    -0.08
    นะนำ
    -0.08
    ững
    -0.07
    ඹ
    -0.07
     hail
    -0.07
     tham
    -0.07
     त्यस
    -0.07
    ोप
    -0.07
     tipi
    -0.07
    POSITIVE LOGITS
    全文
    0.08
     보면
    0.08
     Bram
    0.08
     Employment
    0.08
     Crane
    0.08
    (iv
    0.07
    Subtract
    0.07
    要求
    0.07
    Equation
    0.07
     Morrison
    0.07
    Activations Density 0.026%

    No Known Activations