© 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. 54685
    Prev
    Next
    INDEX
    Explanations

    as/to

    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
    -0.08
    Gel
    -0.08
     tightened
    -0.08
     Merkel
    -0.07
    -0.07
     Kamp
    -0.07
     menuju
    -0.07
     strikes
    -0.07
    rein
    -0.07
    -0.07
    POSITIVE LOGITS
     celui
    0.09
     ours
    0.08
     سایر
    0.07
    cidos
    0.07
    ıca
    0.07
     собой
    0.07
     Pitts
    0.07
     $.
    0.07
     nhau
    0.07
     tils
    0.07
    Activations Density 0.055%
    No Known Activations