© 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. 904
    Prev
    Next
    INDEX
    Explanations

    Memory aids and mnemonics

    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
    upload
    -0.09
    Uploads
    -0.08
    results
    -0.08
    serialize
    -0.08
     dignity
    -0.08
    Transparency
    -0.08
     upload
    -0.08
    submit
    -0.07
     upl
    -0.07
     upgrades
    -0.07
    POSITIVE LOGITS
    口诀
    0.20
     mnemonic
    0.20
     memorize
    0.16
    Mnemonic
    0.15
     remembering
    0.15
    牢记
    0.15
     기억
    0.15
     memor
    0.13
    忆
    0.13
    覚
    0.13
    Activations Density 0.042%

    No Known Activations