Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77571
    Prev
    Next
    INDEX
    Explanations

    draft

    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
     legitim
    -0.08
    िभ
    -0.08
     Ned
    -0.07
    ി�
    -0.07
     Occ
    -0.07
    ijden
    -0.07
    _big
    -0.07
     justified
    -0.07
     Int
    -0.07
    acionais
    -0.07
    POSITIVE LOGITS
    稿
    0.13
    阶段
    0.10
     kasar
    0.10
     drafts
    0.10
    版本
    0.10
    liminary
    0.10
     вариант
    0.09
     اولیه
    0.09
    版
    0.09
     preliminary
    0.09
    Activations Density 0.028%

    No Known Activations