Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13001
    Prev
    Next
    INDEX
    Explanations

    the

    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
    displaystyle
    -0.08
     ironically
    -0.08
    数据显示
    -0.07
    GAN
    -0.07
    配
    -0.07
    -phase
    -0.07
     ધ્યાન
    -0.07
    _LOW
    -0.07
    .low
    -0.07
     tese
    -0.07
    POSITIVE LOGITS
     avenue
    0.08
    wards
    0.08
     пит
    0.08
    088
    0.08
     cabin
    0.07
     corridors
    0.07
    track
    0.07
    boards
    0.07
     оке
    0.07
     household
    0.07
    Activations Density 0.026%

    No Known Activations