© 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. 11-RESID-POST-AA
    11. 64919
    Prev
    Next
    INDEX
    Explanations

    constants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ाता
    -0.08
    rh
    -0.08
    extent
    -0.08
     hammock
    -0.07
    -Ch
    -0.07
    ार्ट
    -0.07
    Ward
    -0.07
    hne
    -0.07
     extent
    -0.07
     saha
    -0.07
    POSITIVE LOGITS
    onged
    0.08
     exercised
    0.07
     legisl
    0.07
    ogat
    0.07
     যেমন
    0.07
    金
    0.07
    （金
    0.07
     fia
    0.07
    猴
    0.07
    lof
    0.07
    Activations Density 0.004%

    No Known Activations