© 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. 45232
    Prev
    Next
    INDEX
    Explanations

    relationship problems

    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
     api
    -0.08
     eina
    -0.08
     above
    -0.07
     ew
    -0.07
     elabor
    -0.07
     ms
    -0.07
     ee
    -0.07
    .va
    -0.07
     els
    -0.07
     cov
    -0.06
    POSITIVE LOGITS
     altogether
    0.10
     complètement
    0.10
    撤
    0.10
     irrev
    0.10
     diseng
    0.10
     permanently
    0.09
     հրաժ
    0.09
    Withdrawal
    0.09
    ყვიტ
    0.09
     Withdrawal
    0.09
    Activations Density 0.112%

    No Known Activations