© 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. 64491
    Prev
    Next
    INDEX
    Explanations

    greater/less than symbols

    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
    getragen
    -0.09
    ಿಟ್ಟ
    -0.08
    tragen
    -0.08
     ula
    -0.08
     Vet
    -0.08
     vengeance
    -0.08
    တော့
    -0.08
    Bmp
    -0.08
    üc
    -0.08
    וגע
    -0.08
    POSITIVE LOGITS
     sister
    0.08
     compar
    0.08
    .Compare
    0.08
     subprocess
    0.07
     lex
    0.07
     mover
    0.07
     prema
    0.07
    तर
    0.07
     الأول
    0.07
    lex
    0.07
    Activations Density 0.035%

    No Known Activations