© 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. 23-RESID-POST-AA
    11. 52201
    Prev
    Next
    INDEX
    Explanations

    German text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    von
    -0.11
    credentials
    -0.11
    Von
    -0.11
    Zum
    -0.11
    booking
    -0.11
    auf
    -0.11
    Als
    -0.11
    Як
    -0.11
    Wenn
    -0.11
    berater
    -0.11
    POSITIVE LOGITS
     Bedürfnisse
    0.14
     andere
    0.13
     geringe
    0.13
     typische
    0.13
     richtige
    0.13
     sogenannte
    0.13
     einzige
    0.13
     Not
    0.13
     spezielle
    0.13
     Definition
    0.12
    Activations Density 0.074%

    No Known Activations