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. 88217
    Prev
    Next
    INDEX
    Explanations

    Professional emails/letters

    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
    roots
    -0.09
    iness
    -0.08
     mundane
    -0.08
    Shaders
    -0.08
     نفسك
    -0.08
    Interestingly
    -0.08
    igual
    -0.08
    ubwo
    -0.07
    غم
    -0.07
    Créer
    -0.07
    POSITIVE LOGITS
     hereby
    0.11
     __________________
    0.10
     www
    0.09
     ©
    0.09
     대한민국
    0.09
     herein
    0.08
     {↵
    0.08
     ООО
    0.08
     Plaintiff
    0.08
    ございます
    0.07
    Activations Density 0.025%

    No Known Activations