© 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. 11-RESID-POST-AA
    11. 1074
    Prev
    Next
    INDEX
    Explanations

    Art styles and moods

    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
    ，但是
    -0.09
     Elig
    -0.08
    -0.08
    less
    -0.07
     fai
    -0.07
    ，但
    -0.07
     rohkem
    -0.07
    -values
    -0.07
    -0.07
    ，不过
    -0.07
    POSITIVE LOGITS
     במשך
    0.09
    ｜
    0.07
     hunter
    0.07
     �
    0.07
     wundersch
    0.07
    เจ
    0.07
    гач
    0.07
    (branch
    0.07
     branche
    0.07
     Warsaw
    0.07
    Activations Density 0.024%
    No Known Activations