© 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. 44314
    Prev
    Next
    INDEX
    Explanations

    perimeter of shapes

    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
    富
    -0.08
     culture
    -0.07
    сек
    -0.07
     abundance
    -0.07
     abund
    -0.07
     populations
    -0.07
    �
    -0.07
    充
    -0.07
    веч
    -0.07
     dosage
    -0.07
    POSITIVE LOGITS
     površ
    0.12
     perimeter
    0.11
     Exterior
    0.11
    Exterior
    0.11
     الخارجية
    0.11
     exterior
    0.11
     поверхность
    0.11
     coastline
    0.11
     BORDER
    0.10
     наруж
    0.10
    Activations Density 0.014%

    No Known Activations