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. 30530
    Prev
    Next
    INDEX
    Explanations

    mathematical problems

    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
     ath
    -0.08
    Laravel
    -0.07
     Wikipedia
    -0.07
    {{
    -0.07
     الواحد
    -0.07
    Claude
    -0.07
    แล้ว
    -0.07
     advent
    -0.07
    ophon
    -0.07
    よう
    -0.07
    POSITIVE LOGITS
     سوى
    0.10
    best
    0.09
    BEST
    0.08
    fri
    0.08
     CONDITION
    0.08
     Worse
    0.08
    කු
    0.07
    las
    0.07
     Keeping
    0.07
     onbek
    0.07
    Activations Density 0.038%

    No Known Activations