© 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. 1323
    Prev
    Next
    INDEX
    Explanations

    expanding

    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
    流水
    -0.08
    交通
    -0.07
    $request
    -0.07
    访
    -0.07
     pisc
    -0.07
     철
    -0.07
    Brain
    -0.07
     depot
    -0.07
     julgamento
    -0.07
    $text
    -0.07
    POSITIVE LOGITS
     Tuesday
    0.08
     Luk
    0.08
    0.07
    െങ്കിൽ
    0.07
     bonds
    0.07
     القوى
    0.07
     Sandy
    0.07
    holders
    0.07
     Appro
    0.07
     Conservative
    0.07
    Activations Density 0.006%
    No Known Activations