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. 61314
    Prev
    Next
    INDEX
    Explanations

    math and physics problems

    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
     quilt
    -0.11
     enviar
    -0.08
     إرسال
    -0.08
     �
    -0.08
    .requests
    -0.08
     schedules
    -0.08
     تقديم
    -0.08
     发
    -0.07
    -outs
    -0.07
     зда
    -0.07
    POSITIVE LOGITS
     Energ
    0.09
     गर्दा
    0.09
     انرژی
    0.08
    energy
    0.08
    energia
    0.08
     വന്ന
    0.08
     énergie
    0.08
     conversion
    0.08
     energi
    0.08
    (loss
    0.08
    Activations Density 0.004%

    No Known Activations