Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 130351
    Prev
    Next
    INDEX
    Explanations

    user consent

    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
     徒
    -0.09
    েউ
    -0.09
    EDS
    -0.08
    Season
    -0.08
     Season
    -0.08
     Fighter
    -0.08
    Rail
    -0.08
    ton
    -0.08
    Airport
    -0.07
    ত্ত
    -0.07
    POSITIVE LOGITS
     brochures
    0.10
     checkbox
    0.09
     स्क्रीन
    0.09
     consent
    0.09
     persuasive
    0.09
     transparency
    0.09
     eindeutig
    0.09
     duidelijke
    0.09
    .checkbox
    0.09
    _checkbox
    0.09
    Activations Density 0.016%

    No Known Activations