© 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. 31355
    Prev
    Next
    INDEX
    Explanations

    hip flexor

    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
     aproveitar
    -0.08
    anfaat
    -0.08
     aprove
    -0.08
     monetary
    -0.08
     nutzt
    -0.08
    untungan
    -0.07
     diesmal
    -0.07
     استف
    -0.07
    anfaatkan
    -0.07
    赛事
    -0.07
    POSITIVE LOGITS
     hips
    0.11
     hip
    0.09
     healthy
    0.09
     कमज
    0.09
     অধিক
    0.09
     unhealthy
    0.09
     स्वस्थ
    0.08
     muscul
    0.08
     कमजोर
    0.08
     insecurity
    0.08
    Activations Density 0.007%

    No Known Activations