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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 96718
    Prev
    Next
    INDEX
    Explanations

    say the ending -ation

    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
     Africa
    -0.09
     Trabal
    -0.08
     Tres
    -0.08
     África
    -0.08
     tremend
    -0.08
    ensitive
    -0.08
     ai
    -0.07
     speel
    -0.07
     reais
    -0.07
     Craft
    -0.07
    POSITIVE LOGITS
    arkeun
    0.09
     hik
    0.08
    ارض
    0.08
     表
    0.08
    KIT
    0.08
    adik
    0.08
    čili
    0.08
    表
    0.08
    umn
    0.07
    eschreven
    0.07
    Activations Density 0.000%

    No Known Activations