© 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. 69177
    Prev
    Next
    INDEX
    Explanations

    block

    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
    _cpu
    -0.10
    _CPU
    -0.09
    .hardware
    -0.08
    foon
    -0.08
     category
    -0.08
    _datas
    -0.08
     controll
    -0.07
    izacion
    -0.07
     Usb
    -0.07
    _wifi
    -0.07
    POSITIVE LOGITS
    删除
    0.09
    删
    0.08
     删除
    0.08
     삭제
    0.08
     Inhalte
    0.08
     emojis
    0.08
     etti
    0.08
    遗漏
    0.08
     paru
    0.08
     omitted
    0.08
    Activations Density 0.004%

    No Known Activations