© 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 EvalsExportsinterp-engineNEWAPI 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. 18843
    Prev
    Next
    INDEX
    Explanations

    是

    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
     is
    -0.17
     είναι
    -0.16
     adalah
    -0.15
     është
    -0.13
     是
    -0.13
     Είναι
    -0.13
     เป็น
    -0.13
     է
    -0.12
     would
    -0.12
    	is
    -0.12
    POSITIVE LOGITS
    一个
    0.18
    为了
    0.16
    因为
    0.14
    骗人的
    0.13
    假的
    0.13
    じめ
    0.12
    骗局吗
    0.12
    由于
    0.12
     blevet
    0.11
    我
    0.11
    Activations Density 0.015%

    No Known Activations