© 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. 48247
    Prev
    Next
    INDEX
    Explanations

    Mont

    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
    iseid
    -0.09
    issé
    -0.08
    тиш
    -0.08
    sera
    -0.08
     предназнач
    -0.08
    yside
    -0.08
     visto
    -0.07
     экземпля
    -0.07
    Ş
    -0.07
    tiques
    -0.07
    POSITIVE LOGITS
    par
    0.10
    mag
    0.08
    ‍മ
    0.08
    Woo
    0.08
    -re
    0.08
    mart
    0.08
    reu
    0.08
    lamp
    0.08
    0.08
    PAR
    0.08
    Activations Density 0.001%
    No Known Activations