© 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. 78466
    Prev
    Next
    INDEX
    Explanations

    brew

    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
    _flash
    -0.09
     Aboriginal
    -0.08
    _el
    -0.08
     lezen
    -0.08
    ترین
    -0.08
    _vect
    -0.08
     faptul
    -0.08
     рассказы
    -0.08
    λύ
    -0.08
     торговли
    -0.07
    POSITIVE LOGITS
     Proposition
    0.08
     proposition
    0.08
     questões
    0.08
     Received
    0.07
    ayment
    0.07
     paquet
    0.07
     Payment
    0.07
     precaution
    0.07
     Sig
    0.07
     PAYMENT
    0.07
    Activations Density 0.001%

    No Known Activations