© 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. 108316
    Prev
    Next
    INDEX
    Explanations

    Hemingway

    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
     sticker
    -0.09
     lockdown
    -0.08
     @_;↵↵
    -0.08
     Retail
    -0.08
     Sticker
    -0.08
    _LED
    -0.07
    徽
    -0.07
     tecnologia
    -0.07
     miss
    -0.07
     recycl
    -0.07
    POSITIVE LOGITS
     Hemingway
    0.09
     море
    0.08
     Ryan
    0.08
     समुद
    0.08
     dipping
    0.08
     शैली
    0.07
    .communication
    0.07
     depression
    0.07
     blog
    0.07
     Deniz
    0.07
    Activations Density 0.002%

    No Known Activations