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. 42387
    Prev
    Next
    INDEX
    Explanations

    3

    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
     weakening
    -0.08
     pennies
    -0.08
     unheard
    -0.08
    揭
    -0.08
    rige
    -0.07
     lawsuits
    -0.07
     ilalim
    -0.07
     sotto
    -0.07
    ிகளில்
    -0.07
     wearer
    -0.07
    POSITIVE LOGITS
     preferably
    0.12
     желательно
    0.09
     Voraussetzung
    0.09
    最新版
    0.09
    choose
    0.08
     compatible
    0.08
     Choose
    0.08
     conducive
    0.08
    -devel
    0.08
     requisito
    0.08
    Activations Density 0.013%

    No Known Activations