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. 60801
    Prev
    Next
    INDEX
    Explanations

    cycle

    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
    fighters
    -0.08
    srv
    -0.08
     geraten
    -0.07
    -0.07
     dring
    -0.07
    stall
    -0.07
     recurrent
    -0.07
     sector
    -0.07
     disguised
    -0.07
    ISH
    -0.07
    POSITIVE LOGITS
    alyze
    0.09
    評価
    0.08
    _analysis
    0.08
    Costs
    0.08
     hinweg
    0.08
    モ
    0.08
    -analysis
    0.08
    tributed
    0.08
     assessment
    0.08
     microscopic
    0.08
    Activations Density 0.002%

    No Known Activations