© 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. 99135
    Prev
    Next
    INDEX
    Explanations

    percent

    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
     있어
    -0.09
    eds
    -0.07
    gad
    -0.07
     dificult
    -0.07
     أم
    -0.07
     алу
    -0.07
    .ob
    -0.07
    .lesson
    -0.07
     국내
    -0.07
    alaan
    -0.07
    POSITIVE LOGITS
     motel
    0.08
    244
    0.07
     ਸਮ
    0.07
    örung
    0.07
    LER
    0.07
     mites
    0.07
    184
    0.07
     podp
    0.07
     plezier
    0.07
     ondersteuning
    0.07
    Activations Density 0.010%

    No Known Activations