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

    Neuronpedia

    APICircuit 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. 30587
    Prev
    Next
    INDEX
    Explanations

    chance

    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
     Bab
    -0.08
    ோக
    -0.08
    க்கு
    -0.08
    கு
    -0.08
     lob
    -0.07
    �
    -0.07
     purposely
    -0.07
     Ezra
    -0.07
     Dam
    -0.07
    Expectation
    -0.07
    POSITIVE LOGITS
    fully
    0.10
     unt
    0.08
     stirring
    0.08
    icao
    0.08
    cup
    0.08
    naire
    0.07
     stir
    0.07
     Eun
    0.07
     imprint
    0.07
     stirred
    0.07
    Activations Density 0.009%

    No Known Activations