© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16324
    Prev
    Next
    INDEX
    Explanations

    membership

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unrealistic
    -0.08
    Trending
    -0.08
    Prices
    -0.08
    imach
    -0.08
     planners
    -0.08
     grapefruit
    -0.08
    _prices
    -0.08
     distracted
    -0.08
     поле
    -0.08
    alaan
    -0.08
    POSITIVE LOGITS
     probation
    0.15
    正式
    0.14
    资格
    0.13
    成为
    0.12
     honorary
    0.11
     eligibility
    0.11
     eligible
    0.11
     convertirse
    0.10
     oficialmente
    0.10
    membership
    0.10
    Activations Density 0.008%

    No Known Activations