© 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. 129113
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     thu
    -0.07
     man
    -0.07
     décidé
    -0.07
     governments
    -0.07
     surveyed
    -0.07
     Governments
    -0.07
    Normal
    -0.07
     road
    -0.07
    ანდ
    -0.07
     quyết
    -0.07
    POSITIVE LOGITS
     infinit
    0.09
    avoid
    0.09
     Nonetheless
    0.08
     avoiding
    0.08
     infinitely
    0.08
     близ
    0.08
     attaining
    0.08
    fortunately
    0.08
     slight
    0.08
     agama
    0.08
    Activations Density 0.023%

    No Known Activations