© 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. 23-RESID-POST-AA
    11. 5412
    Prev
    Next
    INDEX
    Explanations

    say "ry"

    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
     ак
    -0.08
     Гал
    -0.08
     confinement
    -0.08
    eliac
    -0.07
    icultural
    -0.07
     അക്ക
    -0.07
    stellungen
    -0.07
    Ec
    -0.07
    ured
    -0.07
     mirrored
    -0.07
    POSITIVE LOGITS
    ry
    0.14
    rying
    0.13
    ryer
    0.13
    RY
    0.11
    rys
    0.09
     ry
    0.09
    ryw
    0.09
    ryt
    0.08
    ryl
    0.08
     xn
    0.08
    Activations Density 0.001%

    No Known Activations