© 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. 78172
    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
    ENTES
    -0.08
     Elections
    -0.08
    oan
    -0.08
     Achter
    -0.08
     Rift
    -0.08
     Modi
    -0.08
    agsan
    -0.08
    etés
    -0.08
     Ogun
    -0.08
    რობა
    -0.08
    POSITIVE LOGITS
     filesystem
    0.09
    ita
    0.08
     possibly
    0.07
     is
    0.07
     ↵
    0.07
    aug
    0.07
     in
    0.07
     在
    0.07
     è
    0.07
     a
    0.07
    Activations Density 0.296%

    No Known Activations