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. 59269
    Prev
    Next
    INDEX
    Explanations

    VAT

    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
     الجميل
    -0.08
     наслаж
    -0.08
    欣
    -0.08
     ફોન
    -0.08
    clerc
    -0.08
     Lieblings
    -0.08
    verständ
    -0.08
     resent
    -0.07
     erstaun
    -0.07
    Natürlich
    -0.07
    POSITIVE LOGITS
     wajib
    0.11
     verplicht
    0.10
     exemption
    0.10
     obligation
    0.09
     exempt
    0.09
     규모
    0.09
     обяз
    0.08
     obligations
    0.08
     dépass
    0.08
    -own
    0.08
    Activations Density 0.042%

    No Known Activations