© 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. 97297
    Prev
    Next
    INDEX
    Explanations

    code

    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
    icing
    -0.08
     بالف
    -0.07
    〈
    -0.07
     раздраж
    -0.07
    örg
    -0.07
    ▄
    -0.07
     राहत
    -0.07
    ृष्ट
    -0.07
     విక
    -0.07
    骗
    -0.07
    POSITIVE LOGITS
     обла
    0.08
     dependency
    0.07
     সর্ব
    0.07
    홀
    0.07
    _tau
    0.07
     unzip
    0.07
     holder
    0.07
    -wallet
    0.07
    -t
    0.07
     arred
    0.07
    Activations Density 0.000%

    No Known Activations