© 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. 103602
    Prev
    Next
    INDEX
    Explanations

    not needed

    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
     ohne
    -0.10
     without
    -0.09
     Without
    -0.09
     trotz
    -0.09
     WITHOUT
    -0.08
     Ohne
    -0.08
     बिना
    -0.08
     सुनिश्चित
    -0.08
     ללא
    -0.08
    without
    -0.08
    POSITIVE LOGITS
     hoeft
    0.17
     hoeven
    0.17
     unnecessary
    0.17
     unnecessarily
    0.15
     anymore
    0.14
     hoef
    0.13
     вовсе
    0.13
     thanks
    0.13
     sosai
    0.12
     كثيرا
    0.12
    Activations Density 0.048%

    No Known Activations