© 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. 569
    Prev
    Next
    INDEX
    Explanations

    coding instructions

    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
     tights
    -0.08
     blindly
    -0.08
     indeed
    -0.08
     jolloin
    -0.07
     rails
    -0.07
    ，很
    -0.07
     راحت
    -0.07
     //$
    -0.07
     follicles
    -0.07
    っ
    -0.07
    POSITIVE LOGITS
     пожалуйста
    0.11
     Please
    0.11
     bitte
    0.10
    Please
    0.10
     please
    0.10
    please
    0.10
    ，请
    0.10
    ¤
    0.09
     Assume
    0.09
     deverão
    0.09
    Activations Density 0.032%

    No Known Activations