© 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. 30108
    Prev
    Next
    INDEX
    Explanations

    problems' final answers

    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
    leetcode
    -0.09
     wreath
    -0.09
     cops
    -0.09
    围
    -0.08
     domino
    -0.08
     tournaments
    -0.08
     combin
    -0.08
     palindrome
    -0.08
     tableaux
    -0.08
     sequences
    -0.08
    POSITIVE LOGITS
     расчет
    0.15
     calculations
    0.14
     계산
    0.14
     расч
    0.14
     calculation
    0.13
     Calculation
    0.13
     calculated
    0.13
     estimated
    0.13
     cálculo
    0.13
     hesap
    0.13
    Activations Density 0.133%

    No Known Activations