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. 43390
    Prev
    Next
    INDEX
    Explanations

    load balancing

    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
    ותה
    -0.08
     Camden
    -0.08
     eyesight
    -0.08
     dreams
    -0.08
     centimeters
    -0.08
     qualifies
    -0.08
    שט
    -0.08
    .Nullable
    -0.07
     sights
    -0.07
    pey
    -0.07
    POSITIVE LOGITS
     распредел
    0.14
     distributes
    0.13
     нагруз
    0.12
     нагрузки
    0.12
     distribute
    0.12
     توزيع
    0.11
     distribuir
    0.11
     distributing
    0.11
     redistribute
    0.11
     répart
    0.11
    Activations Density 0.005%

    No Known Activations