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. 106252
    Prev
    Next
    INDEX
    Explanations

    Spacing

    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
    ত
    -0.07
     Perfil
    -0.07
     toward
    -0.07
     missions
    -0.07
     perseg
    -0.07
    凌晨
    -0.07
    ammat
    -0.07
     however
    -0.07
     profiles
    -0.07
    .↵//↵
    -0.07
    POSITIVE LOGITS
    排列
    0.10
     breathable
    0.10
     spacing
    0.09
    空气
    0.09
    _spacing
    0.09
     cramped
    0.09
    spacing
    0.09
    Spacing
    0.08
     Wärme
    0.08
    ichtig
    0.08
    Activations Density 0.009%

    No Known Activations