© 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. 45487
    Prev
    Next
    INDEX
    Explanations

    body parts and physical interactions

    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
    /New
    -0.08
    /raw
    -0.08
    alyk
    -0.08
     uusia
    -0.08
    조건
    -0.08
     rohe
    -0.07
     экспер
    -0.07
     graphi
    -0.07
     élus
    -0.07
    ells
    -0.07
    POSITIVE LOGITS
    住
    0.09
     biedt
    0.08
    軽
    0.08
    裙
    0.08
    を
    0.08
     firmly
    0.07
     Firm
    0.07
    く
    0.07
     Appartement
    0.07
     brinda
    0.07
    Activations Density 0.021%

    No Known Activations