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. 102749
    Prev
    Next
    INDEX
    Explanations

    vanishing gradient

    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
     stitched
    -0.08
     Stitch
    -0.08
     stitching
    -0.07
     Shawn
    -0.07
     SPEC
    -0.07
     aansch
    -0.07
     assembled
    -0.07
    指定
    -0.07
     shaking
    -0.07
     Zenith
    -0.07
    POSITIVE LOGITS
    arap
    0.09
    иде
    0.08
    Gef
    0.08
    problemen
    0.08
     diferencial
    0.08
    ämp
    0.08
     yakın
    0.08
    زياء
    0.07
    დილ
    0.07
    /javase
    0.07
    Activations Density 0.001%

    No Known Activations