© 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. 29545
    Prev
    Next
    INDEX
    Explanations

    opening parentheses

    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
    。那么
    -0.09
    。因此
    -0.09
    ，那么
    -0.08
     chimney
    -0.08
     bushes
    -0.08
     Marke
    -0.08
     bounds
    -0.08
    bounds
    -0.08
     Mani
    -0.08
     autoridade
    -0.08
    POSITIVE LOGITS
     fairly
    0.09
    काल
    0.08
     briefly
    0.08
     R
    0.08
     brief
    0.08
     prot
    0.08
    unn
    0.08
     admittedly
    0.08
     chron
    0.08
     supon
    0.07
    Activations Density 0.031%

    No Known Activations