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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19041
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     festivities
    -0.10
     incontourn
    -0.09
     zusammensch
    -0.08
     शादी
    -0.08
     phenomen
    -0.08
     së
    -0.08
     gick
    -0.08
     pape
    -0.08
     dévelop
    -0.08
     લગ્ન
    -0.08
    POSITIVE LOGITS
     Syntax
    0.09
    代码
    0.09
    .leetcode
    0.09
     syntax
    0.09
    Typed
    0.09
     typed
    0.09
     코드
    0.09
     исправ
    0.09
    snippet
    0.09
    コード
    0.09
    Activations Density 0.009%

    No Known Activations