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. 60802
    Prev
    Next
    INDEX
    Explanations

    on

    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
    category
    -0.09
    imente
    -0.09
     flujo
    -0.08
    sembling
    -0.08
    enuous
    -0.08
    ฯ
    -0.08
    otse
    -0.08
     elevar
    -0.08
     undertake
    -0.08
     willing
    -0.07
    POSITIVE LOGITS
     inscriptions
    0.10
    注明
    0.10
    刻
    0.09
     signage
    0.09
    铭
    0.09
     engraved
    0.09
     prominently
    0.09
     estamp
    0.09
     worn
    0.09
    Manufacturer
    0.09
    Activations Density 0.065%

    No Known Activations