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. 43924
    Prev
    Next
    INDEX
    Explanations

    font

    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
     incompet
    -0.08
    agination
    -0.08
    คร
    -0.08
     Eleanor
    -0.08
     compartment
    -0.08
    GENERAL
    -0.08
     surroundings
    -0.08
    Talk
    -0.08
     beginner
    -0.08
    แบ่ง
    -0.07
    POSITIVE LOGITS
     çag
    0.10
     yük
    0.09
     Fonts
    0.08
    woff
    0.08
     geladen
    0.08
     fonts
    0.08
     haɗ
    0.08
     coûte
    0.08
    fonts
    0.08
     ચલ
    0.08
    Activations Density 0.002%

    No Known Activations