© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102139
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     similaire
    -0.09
    كانت
    -0.09
     dégust
    -0.09
    нында
    -0.09
     इसी
    -0.09
    receiver
    -0.09
     semelhante
    -0.08
    блем
    -0.08
     stet
    -0.08
    عيش
    -0.08
    POSITIVE LOGITS
     additional
    0.11
     Additional
    0.10
     zusätzliche
    0.10
     дополнительные
    0.10
     추가
    0.09
     अतिरिक्त
    0.09
    .additional
    0.09
     supplémentaire
    0.09
    เพิ่มเติม
    0.09
    additional
    0.09
    Activations Density 0.019%

    No Known Activations