© 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. 65463
    Prev
    Next
    INDEX
    Explanations

    annelids

    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
     lingü
    -0.08
    微软雅黑
    -0.08
     mono
    -0.08
     phishing
    -0.08
    YAxis
    -0.08
    ғы
    -0.08
    IERC
    -0.07
     Himalayan
    -0.07
     dużo
    -0.07
     arb
    -0.07
    POSITIVE LOGITS
    -length
    0.10
    _segments
    0.09
     lengths
    0.09
    length
    0.08
     Angaben
    0.08
     length
    0.08
    (segment
    0.08
    -Length
    0.08
     segments
    0.08
    长度
    0.08
    Activations Density 0.002%

    No Known Activations