© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31281
    Prev
    Next
    INDEX
    Explanations

    perfect square

    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
     المختلف
    -0.09
    eyo
    -0.08
    /jobs
    -0.08
     Cosmos
    -0.08
     décide
    -0.08
     تصمیم
    -0.08
     menentukan
    -0.08
     determines
    -0.08
     decides
    -0.08
    blocking
    -0.08
    POSITIVE LOGITS
     quadratic
    0.09
     frequentemente
    0.09
     repeated
    0.09
     repetitive
    0.09
     frequently
    0.08
     repeating
    0.08
     repeat
    0.08
     frequent
    0.08
    quadr
    0.08
     recurrent
    0.08
    Activations Density 0.075%

    No Known Activations