© 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. 51996
    Prev
    Next
    INDEX
    Explanations

    German language

    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
    Not in Any Lists

    No Comments

    Negative Logits
    geleverd
    -0.12
     Förderung
    -0.12
     Gebruik
    -0.12
    geleid
    -0.12
     Lernen
    -0.11
     geholpen
    -0.11
     Speicherung
    -0.11
     Lieferung
    -0.11
     Durchführung
    -0.11
     получение
    -0.11
    POSITIVE LOGITS
     widers
    0.13
     nachvoll
    0.13
     akkurat
    0.12
     beurte
    0.12
     heraus
    0.12
     zusammen
    0.12
     genauer
    0.12
     herunter
    0.12
     eindeutig
    0.11
     exakt
    0.11
    Activations Density 0.011%

    No Known Activations