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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 68993
    Prev
    Next
    INDEX
    Explanations

    key

    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
     것
    -0.08
    Pojo
    -0.08
    uator
    -0.07
    Tidak
    -0.07
    Pode
    -0.07
     teve
    -0.07
     samu
    -0.07
     కూడ
    -0.07
    怎么办
    -0.07
    Cela
    -0.07
    POSITIVE LOGITS
     purpose
    0.09
    负责人
    0.08
     MMM
    0.08
    主要
    0.08
     responsible
    0.08
     उद्देश्य
    0.08
     Responsibilities
    0.08
    特徴
    0.07
     responsibilities
    0.07
    特点
    0.07
    Activations Density 0.017%

    No Known Activations