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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95825
    Prev
    Next
    INDEX
    Explanations

    independent

    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
    kw
    -0.09
    -packed
    -0.08
    큰
    -0.08
    ządz
    -0.08
    .food
    -0.08
     kw
    -0.07
     đoàn
    -0.07
     роботи
    -0.07
     Packed
    -0.07
    kul
    -0.07
    POSITIVE LOGITS
    第三
    0.09
    专家
    0.09
    机构
    0.09
     assess
    0.09
     impartial
    0.09
     विशेषज्ञ
    0.08
    专业
    0.08
     experto
    0.08
     verify
    0.08
     community
    0.08
    Activations Density 0.008%

    No Known Activations