© 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. 222
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    Runner
    -0.10
     установлен
    -0.09
     Pounds
    -0.09
     pounds
    -0.09
     Runner
    -0.09
    айн
    -0.08
     указан
    -0.08
    ууд
    -0.08
    .Manifest
    -0.08
     instalaciones
    -0.08
    POSITIVE LOGITS
     sentences
    0.13
     utter
    0.12
     verbal
    0.12
     spoken
    0.12
    表达
    0.11
     বক্ত
    0.10
     conversational
    0.10
     conveying
    0.10
    句
    0.10
     표현
    0.10
    Activations Density 0.025%

    No Known Activations