© 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. 75644
    Prev
    Next
    INDEX
    Explanations

    caffeine dosage

    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
    wag
    -0.08
    ุล
    -0.08
    details
    -0.07
    ITLE
    -0.07
    RA
    -0.07
    _wr
    -0.07
     wasting
    -0.07
    1
    -0.07
    WD
    -0.07
    -but
    -0.07
    POSITIVE LOGITS
     plagiarism
    0.09
     caffeine
    0.09
     brom
    0.09
     Chocolate
    0.09
     odgovor
    0.08
     մեղ
    0.08
    攻击
    0.08
     Francis
    0.08
     attacks
    0.08
    ലി
    0.08
    Activations Density 0.005%

    No Known Activations