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. 48319
    Prev
    Next
    INDEX
    Explanations

    for to

    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
    .commit
    -0.08
    ↵ ↵
    -0.08
    "]
    -0.08
    appar
    -0.08
     aquela
    -0.07
     einde
    -0.07
     proverbial
    -0.07
     некотор
    -0.07
     બદલ
    -0.07
     світ
    -0.07
    POSITIVE LOGITS
     specifics
    0.09
     говорить
    0.09
    方面
    0.09
    另一方面
    0.09
     nutshell
    0.08
     naman
    0.08
     meanwhile
    0.08
     الجانب
    0.08
     interaction
    0.07
    来说
    0.07
    Activations Density 0.057%

    No Known Activations