© 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. 6276
    Prev
    Next
    INDEX
    Explanations

    Brisbane/Fuzhou

    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
     Barca
    -0.08
    ेत्र
    -0.08
     Barbosa
    -0.08
     Hau
    -0.08
    apea
    -0.08
     trợ
    -0.07
    ển
    -0.07
     ナ
    -0.07
    ̭
    -0.07
     assister
    -0.07
    POSITIVE LOGITS
    uku
    0.08
    uj
    0.08
     iure
    0.08
    JW
    0.07
    ij
    0.07
     itin
    0.07
    itch
    0.07
    alian
    0.07
    uk
    0.07
     jj
    0.07
    Activations Density 0.000%

    No Known Activations