© 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. 44605
    Prev
    Next
    INDEX
    Explanations

    respond in only english

    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
     автоном
    -0.09
    につ
    -0.08
    ját
    -0.08
     logically
    -0.08
     département
    -0.08
     sentimento
    -0.08
     autonom
    -0.08
     basketball
    -0.07
     матери
    -0.07
     الخبر
    -0.07
    POSITIVE LOGITS
    ाली
    0.08
     Palette
    0.07
    0.07
    Palette
    0.07
     tattoos
    0.07
    amise
    0.07
    lash
    0.07
    าป
    0.07
    tle
    0.07
     Muy
    0.07
    Activations Density 0.005%
    No Known Activations