© 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. 48138
    Prev
    Next
    INDEX
    Explanations

    Anesthesia

    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
    оур
    -0.08
    'adore
    -0.08
    ිරි
    -0.08
    dan
    -0.08
    óttir
    -0.07
     unexpectedly
    -0.07
    ต้อง
    -0.07
    ｡
    -0.07
    226
    -0.07
     stages
    -0.07
    POSITIVE LOGITS
    hetics
    0.23
    het
    0.22
    hetic
    0.21
    hes
    0.18
    hetically
    0.17
    hesia
    0.17
    hetical
    0.17
    heth
    0.16
    h
    0.15
    esia
    0.14
    Activations Density 0.002%

    No Known Activations