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. 11-RESID-POST-AA
    6. 58473
    Prev
    Next
    INDEX
    Explanations

    active

    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
     biologique
    -0.08
     dangerous
    -0.08
     Bord
    -0.07
     risk
    -0.07
     NOAA
    -0.07
     IDisposable
    -0.07
     опас
    -0.07
     nguy
    -0.07
     year
    -0.07
    .year
    -0.07
    POSITIVE LOGITS
     Slight
    0.08
    egang
    0.08
    	If
    0.08
     ўз
    0.07
     deepest
    0.07
     саб
    0.07
     Ceará
    0.07
     fə
    0.07
     Mandel
    0.07
     Pernambuco
    0.07
    Activations Density 0.001%

    No Known Activations