© 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. 11-RESID-POST-AA
    11. 68153
    Prev
    Next
    INDEX
    Explanations

    iji

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vha
    -0.08
     inscr
    -0.08
     uren
    -0.08
    ်
    -0.08
     prepor
    -0.08
     рә
    -0.08
    ავად
    -0.08
     wages
    -0.08
     precum
    -0.08
     ತಾಲ
    -0.08
    POSITIVE LOGITS
    trap
    0.09
     Trap
    0.08
    trend
    0.08
    这里
    0.08
    imet
    0.08
     Ac
    0.07
    Trap
    0.07
     Here
    0.07
     Wireless
    0.07
    Here
    0.07
    Activations Density 0.000%

    No Known Activations