© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 52209
    Prev
    Next
    INDEX
    Explanations

    say "ish"

    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
    Negative Logits
    ्ट्र
    -0.08
    妞
    -0.07
    波
    -0.07
    keits
    -0.07
     Wai
    -0.07
    lop
    -0.07
    rou
    -0.07
    ------+------+
    -0.07
    mia
    -0.07
    ్ట్ర
    -0.07
    POSITIVE LOGITS
    ishing
    0.20
    ishments
    0.19
    ishes
    0.19
    ishment
    0.18
    ished
    0.18
    ISHED
    0.15
    ish
    0.15
    ishable
    0.15
    itures
    0.14
    ిష
    0.13
    Activations Density 0.011%

    No Known Activations