Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 48988
    Prev
    Next
    INDEX
    Explanations

    Multilingual

    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
    든
    -0.09
     sometime
    -0.08
    пі
    -0.08
    ехать
    -0.08
    Pv
    -0.08
     правило
    -0.08
     {.
    -0.07
    кер
    -0.07
     vins
    -0.07
     Sikh
    -0.07
    POSITIVE LOGITS
     desperd
    0.10
     clutter
    0.10
    ,提高
    0.10
     reliance
    0.09
     unnecessarily
    0.09
     overwhelm
    0.09
     hoeven
    0.09
     hassle
    0.09
     unnecessary
    0.09
     hassles
    0.09
    Activations Density 0.124%

    No Known Activations