© 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. 94595
    Prev
    Next
    INDEX
    Explanations

    nose

    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
    יו
    -0.08
     コ
    -0.07
    Mun
    -0.07
     Lau
    -0.07
     pall
    -0.07
     মোক
    -0.07
    ೇ
    -0.07
     Servlet
    -0.07
     manner
    -0.07
    ète
    -0.06
    POSITIVE LOGITS
    ikon
    0.08
     finger
    0.08
    leisten
    0.08
    尖
    0.08
     Relief
    0.08
     fingers
    0.08
    spots
    0.08
     Quite
    0.07
     gang
    0.07
    worthy
    0.07
    Activations Density 0.002%

    No Known Activations