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. 11936
    Prev
    Next
    INDEX
    Explanations

    ${

    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
     offiziellen
    -0.08
    င်း
    -0.07
     delo
    -0.07
    UNK
    -0.07
    ৫
    -0.07
    

    -0.07
     indul
    -0.07
    _DECREF
    -0.07
                   
    -0.07
    ADING
    -0.07
    POSITIVE LOGITS
     वार
    0.08
     Enterprises
    0.08
    경제
    0.07
    Cole
    0.07
    ilh
    0.07
     electrically
    0.07
     соб
    0.07
    ipps
    0.07
     firme
    0.07
     lưu
    0.07
    Activations Density 0.000%

    No Known Activations