© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 96
    Prev
    Next
    INDEX
    Explanations

    rubric

    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
     Material
    -0.08
     materiale
    -0.08
    .material
    -0.08
    Material
    -0.08
     strongest
    -0.08
     ге
    -0.07
    koz
    -0.07
    _GPU
    -0.07
    .hardware
    -0.07
     Edo
    -0.07
    POSITIVE LOGITS
     rubric
    0.16
    评分
    0.12
     критер
    0.11
     checklist
    0.11
     kriter
    0.10
     rú
    0.10
     scoring
    0.10
     critérios
    0.10
     шк
    0.10
     beoord
    0.10
    Activations Density 0.005%

    No Known Activations