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. 77358
    Prev
    Next
    INDEX
    Explanations

    (

    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
     IT
    -0.09
     مواقع
    -0.08
     IM
    -0.08
    IT
    -0.08
     lives
    -0.08
    ÍT
    -0.07
    Hop
    -0.07
    eté
    -0.07
     миллионов
    -0.07
     communities
    -0.07
    POSITIVE LOGITS
     Powers
    0.09
     woodworking
    0.08
    expand
    0.08
     defamatory
    0.08
     expand
    0.08
     pourriez
    0.08
     repeatedly
    0.08
    derive
    0.08
     polynomial
    0.08
     powers
    0.08
    Activations Density 0.020%

    No Known Activations