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. 101703
    Prev
    Next
    INDEX
    Explanations

    remove duplicates

    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
    anol
    -0.08
    ioned
    -0.07
     Eph
    -0.07
    eban
    -0.07
     budget
    -0.07
     woke
    -0.07
    ่วย
    -0.07
     regress
    -0.07
     despi
    -0.07
    uros
    -0.07
    POSITIVE LOGITS
     []).
    0.09
     ISSUE
    0.08
     коллектив
    0.08
     [])↵
    0.08
     existentes
    0.08
     अम
    0.08
     количе
    0.08
     средство
    0.08
     colectiva
    0.08
     автоматы
    0.08
    Activations Density 0.003%

    No Known Activations