© 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. 91244
    Prev
    Next
    INDEX
    Explanations

    coverage

    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
     steward
    -0.08
     सौ
    -0.08
     Robertson
    -0.08
     привод
    -0.07
     turn
    -0.07
    ponsor
    -0.07
     pomoc
    -0.07
     välja
    -0.07
    469
    -0.07
     Zar
    -0.07
    POSITIVE LOGITS
     coverage
    0.13
     Coverage
    0.13
    Coverage
    0.12
    覆盖
    0.12
    coverage
    0.12
     കവ
    0.10
     कव
    0.09
    射
    0.09
    .cover
    0.09
     cobertura
    0.08
    Activations Density 0.014%

    No Known Activations