© 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. 29603
    Prev
    Next
    INDEX
    Explanations

    cartoon shows

    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
     Austen
    -0.09
     RENT
    -0.08
     asum
    -0.08
     fai
    -0.08
     ISBN
    -0.08
     Wirk
    -0.08
     requirements
    -0.07
     renting
    -0.07
     verkocht
    -0.07
     aprovado
    -0.07
    POSITIVE LOGITS
    悠
    0.10
    Classic
    0.10
     comedian
    0.09
    visitor
    0.08
    -famous
    0.08
     vener
    0.08
     clásico
    0.08
     Knights
    0.08
     clássico
    0.08
     famous
    0.08
    Activations Density 0.002%

    No Known Activations