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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 88210
    Prev
    Next
    INDEX
    Explanations

    narrow

    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
    (patient
    -0.08
    Mixer
    -0.07
    Patrick
    -0.07
     Patrick
    -0.07
    混
    -0.07
    coa
    -0.07
     постоянно
    -0.07
     mix
    -0.07
    .prevent
    -0.07
    .mix
    -0.07
    POSITIVE LOGITS
     narrowly
    0.10
     Scope
    0.09
     transactional
    0.09
     ವ್ಯಾಪ
    0.09
    scope
    0.09
    Scope
    0.09
     نطاق
    0.09
     niche
    0.09
     narrower
    0.09
     scope
    0.09
    Activations Density 0.035%

    No Known Activations