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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 96769
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
     രൂപ
    -0.08
    ความคิดเห็น
    -0.08
     ხალხ
    -0.08
    ाजिक
    -0.07
     համայն
    -0.07
    AREN
    -0.07
     uumm
    -0.07
     identifiable
    -0.07
    .embed
    -0.07
     ий
    -0.07
    POSITIVE LOGITS
     escritura
    0.10
     desenho
    0.10
     Schreiben
    0.10
     automatique
    0.09
     dessin
    0.09
     char
    0.09
     encontrados
    0.09
     dibujo
    0.09
     écrire
    0.09
     automática
    0.09
    Activations Density 0.004%

    No Known Activations