© 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. 29535
    Prev
    Next
    INDEX
    Explanations

    felt

    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
     заб
    -0.08
     modifies
    -0.08
     mistakes
    -0.08
     becomes
    -0.08
     це
    -0.07
     drastically
    -0.07
     щ
    -0.07
     utilizes
    -0.07
     это
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    ，也是
    0.16
    ，希望
    0.10
    之一
    0.10
    -là
    0.09
    也是
    0.09
     yüzden
    0.09
    ，因为
    0.09
    !↵↵↵
    0.08
    。当然
    0.08
     bolo
    0.08
    Activations Density 0.146%

    No Known Activations