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. 103158
    Prev
    Next
    INDEX
    Explanations

    makes sense

    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
    ấn
    -0.09
    -0.08
     मैदान
    -0.08
     MOBILE
    -0.07
     हस्त
    -0.07
    lic
    -0.07
     സംഘ
    -0.07
     metam
    -0.07
     sifat
    -0.07
    Mobile
    -0.07
    POSITIVE LOGITS
    意义
    0.10
     sentido
    0.10
     смысл
    0.10
    合理
    0.09
     смыс
    0.09
    逻
    0.09
     معنى
    0.09
     razão
    0.09
     Sense
    0.08
     sentidos
    0.08
    Activations Density 0.012%

    No Known Activations