© 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. 95231
    Prev
    Next
    INDEX
    Explanations

    Newton

    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
    December
    -0.10
    November
    -0.09
     मुद
    -0.09
    caught
    -0.08
    Vocabulary
    -0.08
    Files
    -0.08
    Torrent
    -0.08
    Nov
    -0.08
     Vict
    -0.08
     December
    -0.08
    POSITIVE LOGITS
     pusat
    0.08
    所在
    0.08
     cent
    0.08
    _plane
    0.08
     centroid
    0.08
     لون
    0.07
     plages
    0.07
    联系人
    0.07
     LR
    0.07
     பால
    0.07
    Activations Density 0.000%

    No Known Activations