© 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. 44485
    Prev
    Next
    INDEX
    Explanations

    1

    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
     Maur
    -0.08
     Mega
    -0.07
     constit
    -0.07
     aanvull
    -0.07
     Mathieu
    -0.07
     пись
    -0.07
     knowledgeable
    -0.07
     Yale
    -0.07
     realized
    -0.07
    .YELLOW
    -0.07
    POSITIVE LOGITS
     वे
    0.08
     بض
    0.08
     با
    0.07
     امر
    0.07
     smash
    0.07
    /week
    0.07
    ృష్ట
    0.07
    ەپ
    0.07
     فار
    0.07
     titul
    0.07
    Activations Density 0.000%

    No Known Activations