© 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. 54589
    Prev
    Next
    INDEX
    Explanations

    character encoding/replacements

    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
     Necklace
    -0.08
     honey
    -0.08
     Perm
    -0.08
     Boss
    -0.07
     Games
    -0.07
     Rats
    -0.07
     Machinery
    -0.07
     Worm
    -0.07
     Fil
    -0.07
    _codegen
    -0.07
    POSITIVE LOGITS
     強
    0.08
     portanto
    0.08
    '||
    0.08
     beeinfl
    0.07
    Silent
    0.07
     reinforce
    0.07
     causada
    0.07
    ����
    0.07
     informing
    0.07
     returning
    0.07
    Activations Density 0.001%

    No Known Activations