© 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. 11-RESID-POST-AA
    11. 47450
    Prev
    Next
    INDEX
    Explanations

    start continue

    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
     пределах
    -0.09
     Souls
    -0.09
    tranger
    -0.08
    credential
    -0.08
    óvel
    -0.08
     слоя
    -0.08
    astian
    -0.08
     apaixon
    -0.08
     المرك
    -0.08
     selective
    -0.08
    POSITIVE LOGITS
    Remaining
    0.11
    会议
    0.10
     बैठक
    0.09
     সভ
    0.09
    _remaining
    0.09
     remaining
    0.09
    Agenda
    0.09
     الاجتماع
    0.09
    Lunch
    0.08
    Resume
    0.08
    Activations Density 0.032%

    No Known Activations