© 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. 68265
    Prev
    Next
    INDEX
    Explanations

    reviews

    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
     gambler
    -0.09
     CLLocation
    -0.08
     missiles
    -0.08
     Werbung
    -0.08
     versucht
    -0.07
     compartments
    -0.07
     Prelude
    -0.07
     afla
    -0.07
     elementi
    -0.07
     sumin
    -0.07
    POSITIVE LOGITS
    审
    0.12
    审核
    0.12
    レビュー
    0.11
    -reviewed
    0.10
    -review
    0.10
    意见
    0.10
    Reviewer
    0.10
     리뷰
    0.10
     അഭിപ്രായ
    0.10
     reviewers
    0.10
    Activations Density 0.005%

    No Known Activations