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. 54273
    Prev
    Next
    INDEX
    Explanations

    code

    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
    力量
    -0.09
     nanging
    -0.08
     激
    -0.08
     jam
    -0.07
     solutions
    -0.07
     klasik
    -0.07
     hunter
    -0.07
     vik
    -0.07
     vaks
    -0.07
     driving
    -0.07
    POSITIVE LOGITS
     offsetof
    0.10
    offsetof
    0.09
     befindet
    0.08
    _Position
    0.08
    PROPERTY
    0.08
    28
    0.08
     gibt
    0.08
    附近
    0.08
     sofre
    0.08
    gep
    0.08
    Activations Density 0.004%

    No Known Activations