© 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. 3-RESID-POST-AA
    11. 12842
    Prev
    Next
    INDEX
    Explanations

    loop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     આપવા
    -0.08
     Siya
    -0.07
     vec
    -0.07
    şe
    -0.07
     mu
    -0.07
    lim
    -0.07
     Setting
    -0.07
    ર્ય
    -0.07
    _mu
    -0.07
     trin
    -0.07
    POSITIVE LOGITS
     تك
    0.08
    embo
    0.08
     telles
    0.08
     நடவட
    0.07
     कृ
    0.07
    Additionally
    0.07
     beroep
    0.07
     ಕ್ರಮ
    0.07
     barefoot
    0.07
     במד
    0.07
    Activations Density 0.001%

    No Known Activations