© 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. 7-RESID-POST-AA
    11. 906
    Prev
    Next
    INDEX
    Explanations

    gold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manche
    -0.08
    .startswith
    -0.07
    _pickle
    -0.07
     granny
    -0.07
     Symposium
    -0.07
    菜
    -0.07
     enr
    -0.07
    hattan
    -0.07
     mre
    -0.07
     Modi
    -0.07
    POSITIVE LOGITS
     বাস
    0.08
    оч
    0.07
     خل
    0.07
    ап
    0.07
     Tum
    0.07
    iliki
    0.07
     pomp
    0.07
    latin
    0.07
     Nossa
    0.07
     Yun
    0.07
    Activations Density 0.004%

    No Known Activations