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. 49229
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
     света
    -0.08
     jad
    -0.08
    ્યાન
    -0.08
     pray
    -0.07
    gadas
    -0.07
     Y
    -0.07
     baptized
    -0.07
    гун
    -0.07
     gâ
    -0.07
     點
    -0.07
    POSITIVE LOGITS
    Kurz
    0.08
    Cord
    0.07
     impost
    0.07
    (if
    0.07
     zz
    0.07
    زع
    0.07
    袋
    0.07
     excess
    0.07
     veroor
    0.07
    0.07
    Activations Density 0.005%

    No Known Activations