© 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. 26540
    Prev
    Next
    INDEX
    Explanations

    data structures code

    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
     deduction
    -0.09
     culprit
    -0.08
     deductions
    -0.08
    zni
    -0.08
     kid
    -0.08
     compounds
    -0.07
    자로
    -0.07
     parade
    -0.07
     originale
    -0.07
     проблему
    -0.07
    POSITIVE LOGITS
     初始化
    0.09
    初始化
    0.09
    	init
    0.09
    .Initialize
    0.09
     initialized
    0.09
     initiate
    0.09
    .promise
    0.08
     Init
    0.08
     Acho
    0.08
    .init
    0.08
    Activations Density 0.004%

    No Known Activations