© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 49672
    Prev
    Next
    INDEX
    Explanations

    say "reds"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omy
    -0.10
     基
    -0.09
     bbw
    -0.08
     Joh
    -0.08
     Deel
    -0.08
     Rayon
    -0.08
     Sink
    -0.08
     centraal
    -0.08
    asarkan
    -0.08
     天天
    -0.08
    POSITIVE LOGITS
    -dollar
    0.10
    reds
    0.10
    -word
    0.09
     dollars
    0.09
    -price
    0.08
    -digit
    0.08
    -u
    0.08
    -degree
    0.08
    -value
    0.08
    -profit
    0.08
    Activations Density 0.004%

    No Known Activations