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. 106019
    Prev
    Next
    INDEX
    Explanations

    Point-of-care testing

    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
     môn
    -0.09
    precation
    -0.08
     erosion
    -0.08
     भवन
    -0.08
     resurrect
    -0.08
     पीछे
    -0.08
     fant
    -0.08
    Buildings
    -0.08
    Accommodation
    -0.08
     dilation
    -0.08
    POSITIVE LOGITS
    快速
    0.12
    迅
    0.11
     handheld
    0.11
     Quick
    0.11
     assays
    0.11
     త్వర
    0.11
     cepat
    0.11
     quick
    0.11
     rapid
    0.11
     Portable
    0.11
    Activations Density 0.013%

    No Known Activations