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. 112186
    Prev
    Next
    INDEX
    Explanations

    instructions/requirements

    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
     Xamarin
    -0.08
     reversed
    -0.08
     enquanto
    -0.07
     while
    -0.07
     toet
    -0.07
     elet
    -0.07
    NS
    -0.07
     partly
    -0.07
    xea
    -0.07
     electrode
    -0.07
    POSITIVE LOGITS
     promptly
    0.11
     давно
    0.09
     segera
    0.09
     lest
    0.09
     agres
    0.09
    及时
    0.09
    ,否则
    0.09
     almeno
    0.09
     actualizar
    0.09
     pendientes
    0.09
    Activations Density 0.099%

    No Known Activations