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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58447
    Prev
    Next
    INDEX
    Explanations

    form

    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
     Phillips
    -0.08
     વૃ
    -0.08
     Riding
    -0.07
     Keynes
    -0.07
     kort
    -0.07
     वृद्धि
    -0.07
     Fø
    -0.07
     લીધ
    -0.07
     मुताबिक
    -0.07
    amic
    -0.07
    POSITIVE LOGITS
    ください
    0.09
    Except
    0.08
    .Ex
    0.08
    ,以
    0.08
    泄
    0.08
    露
    0.07
     except
    0.07
     أنحاء
    0.07
    PD
    0.07
     EVER
    0.07
    Activations Density 0.007%

    No Known Activations