© 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. 75653
    Prev
    Next
    INDEX
    Explanations

    code symbols

    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
     Isabel
    -0.10
     endorsements
    -0.09
     baroh
    -0.09
     endorsed
    -0.09
     काळ
    -0.09
     деть
    -0.08
     მიუხედავად
    -0.08
    adaky
    -0.08
     edhe
    -0.08
     tiring
    -0.08
    POSITIVE LOGITS
    이라는
    0.08
    Ok
    0.08
     вій
    0.08
     내부
    0.07
    Description
    0.07
    0.07
    Translation
    0.07
    Tree
    0.07
    Timeout
    0.07
    Variable
    0.07
    Activations Density 0.045%
    No Known Activations