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. 44157
    Prev
    Next
    INDEX
    Explanations

    referred

    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
    स्ती
    -0.08
     admitted
    -0.07
    ग
    -0.07
    ’exposition
    -0.07
     폭
    -0.07
     Prosper
    -0.07
    seb
    -0.07
     Picasso
    -0.07
     அழ
    -0.07
     jede
    -0.07
    POSITIVE LOGITS
    Self
    0.08
     unanimously
    0.08
     hjälpa
    0.08
    (utils
    0.08
    ▫
    0.08
     Self
    0.08
     prender
    0.08
    atu
    0.07
    دمات
    0.07
     bantuan
    0.07
    Activations Density 0.024%

    No Known Activations