© 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. 23-RESID-POST-AA
    11. 96351
    Prev
    Next
    INDEX
    Explanations

    Geographic and economic data

    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
     quantidade
    -0.09
     yii
    -0.08
    量
    -0.08
    Quantity
    -0.08
     reales
    -0.08
     nyata
    -0.08
     réel
    -0.08
     Quantity
    -0.08
     amount
    -0.08
     reale
    -0.08
    POSITIVE LOGITS
     Panc
    0.08
     Hé
    0.08
    .compat
    0.08
    .flatten
    0.08
     Israelis
    0.07
    בור
    0.07
     Formular
    0.07
     Antwort
    0.07
     Oberfläche
    0.07
     Pil
    0.07
    Activations Density 0.002%

    No Known Activations