© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 109880
    Prev
    Next
    INDEX
    Explanations

    Version incompatibility

    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
    Negative Logits
     altru
    -0.08
     Steiner
    -0.08
    ですね
    -0.07
    яло
    -0.07
     слово
    -0.07
     стане
    -0.07
     ясно
    -0.07
     niente
    -0.07
     mosque
    -0.07
     aloud
    -0.07
    POSITIVE LOGITS
    Compatibility
    0.15
     compatibility
    0.15
     incompatible
    0.15
    compat
    0.15
     Compatibility
    0.15
    版本
    0.15
     kompat
    0.14
     incompat
    0.14
     compatible
    0.14
    compatible
    0.14
    Activations Density 0.023%

    No Known Activations