© 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. 68602
    Prev
    Next
    INDEX
    Explanations

    Biomechanical/medical issues

    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
    aiset
    -0.08
    Tema
    -0.08
    Come
    -0.08
    teness
    -0.08
    人才
    -0.08
    etten
    -0.08
    Talent
    -0.08
    anais
    -0.08
     баста
    -0.08
    шеб
    -0.08
    POSITIVE LOGITS
     нагруз
    0.13
     stresses
    0.12
     부담
    0.11
     stress
    0.11
     Belast
    0.11
     Stress
    0.11
     तनाव
    0.11
     currents
    0.11
     нагрузки
    0.11
     stressful
    0.11
    Activations Density 0.020%

    No Known Activations