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. 45484
    Prev
    Next
    INDEX
    Explanations

    service recipients

    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
    اسب
    -0.08
    ithiol
    -0.08
     terraces
    -0.07
     gelief
    -0.07
     Hoch
    -0.07
     진행
    -0.07
    산
    -0.07
    Poi
    -0.07
    أت
    -0.07
    饰
    -0.07
    POSITIVE LOGITS
    firstname
    0.08
     that'll
    0.07
     silicone
    0.07
     Keyword
    0.07
     doon
    0.07
     yo
    0.07
    (join
    0.07
     cortex
    0.07
    (answer
    0.07
    oola
    0.07
    Activations Density 0.019%

    No Known Activations