© 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. 3-RESID-POST-AA
    11. 13228
    Prev
    Next
    INDEX
    Explanations

    erster

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quear
    -0.09
    倒
    -0.09
     colo
    -0.08
    कों
    -0.07
    que
    -0.07
     hu
    -0.07
     karşı
    -0.07
    続
    -0.07
    quen
    -0.07
    ORTH
    -0.07
    POSITIVE LOGITS
     elder
    0.09
     Babys
    0.09
     ober
    0.08
     вклад
    0.08
     spit
    0.08
    .gb
    0.08
    BF
    0.08
     pact
    0.08
     Gamble
    0.08
    .rot
    0.07
    Activations Density 0.002%

    No Known Activations