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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 59682
    Prev
    Next
    INDEX
    Explanations

    检

    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
     bew
    -0.08
     जाग
    -0.08
     cake
    -0.07
     employs
    -0.07
     cooper
    -0.07
     empf
    -0.07
    曲
    -0.07
    -0.07
     autor
    -0.07
    agar
    -0.07
    POSITIVE LOGITS
     Bose
    0.08
    .gre
    0.08
     الأد
    0.08
     Å
    0.08
     fath
    0.07
    ว
    0.07
     tahu
    0.07
    不起
    0.07
     зрения
    0.07
     Antio
    0.07
    Activations Density 0.005%

    No Known Activations