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. 112070
    Prev
    Next
    INDEX
    Explanations

    symptoms

    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
    -0.09
     equil
    -0.08
     Titanium
    -0.08
    лица
    -0.07
    ที
    -0.07
    инка
    -0.07
     imaging
    -0.07
    отерап
    -0.07
     TI
    -0.07
     الطبية
    -0.07
    POSITIVE LOGITS
     procrast
    0.10
     disliked
    0.08
     fasting
    0.08
    學生
    0.08
     anxious
    0.08
     dë
    0.08
     vergeet
    0.08
     difficultés
    0.08
     obsession
    0.07
    uas
    0.07
    Activations Density 0.005%

    No Known Activations