© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54412
    Prev
    Next
    INDEX
    Explanations

    code related to flags

    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
     représ
    -0.08
    යන්
    -0.08
     Norden
    -0.08
     Kel
    -0.08
     tejidos
    -0.08
     כיום
    -0.08
    ャ
    -0.08
     histories
    -0.08
    Umb
    -0.08
     tarik
    -0.08
    POSITIVE LOGITS
    考试
    0.13
     grader
    0.12
    題
    0.11
     student's
    0.11
    题
    0.11
    leetcode
    0.11
    .exercise
    0.11
     öğrenc
    0.11
     제출
    0.11
    contest
    0.11
    Activations Density 0.029%

    No Known Activations