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. 58574
    Prev
    Next
    INDEX
    Explanations

    legitimate

    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
     прин
    -0.08
     compatibility
    -0.08
    -bedroom
    -0.08
    compat
    -0.07
    iode
    -0.07
    zhi
    -0.07
     Fate
    -0.07
    691
    -0.07
     voraus
    -0.07
     Compatibility
    -0.07
    POSITIVE LOGITS
    -looking
    0.10
    -benar
    0.09
    imately
    0.09
     legitimate
    0.09
    itimate
    0.08
    还是假的
    0.08
    理由
    0.08
    ێ
    0.07
    ά
    0.07
     יותר
    0.07
    Activations Density 0.010%

    No Known Activations