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. 43185
    Prev
    Next
    INDEX
    Explanations

    can

    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
    Shape
    -0.08
     federally
    -0.07
    Support
    -0.07
     versch
    -0.07
     modern
    -0.07
     ferry
    -0.07
    haus
    -0.07
    Har
    -0.07
    ত্ব
    -0.07
    Align
    -0.06
    POSITIVE LOGITS
     alvast
    0.10
     արդեն
    0.10
     🙂
    0.10
     meteen
    0.09
     تأتي
    0.09
     उपलब
    0.09
     eitth
    0.09
    เอียด
    0.09
     առաջարկ
    0.09
    лардың
    0.09
    Activations Density 0.040%

    No Known Activations