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. 15-RESID-POST-AA
    6. 19491
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diğer
    -0.08
     otros
    -0.08
    .reduce
    -0.08
     reducir
    -0.08
    :
    -0.08
     மற்ற
    -0.08
    iembre
    -0.08
     மட்டும்
    -0.07
     மாற்ற
    -0.07
     வீர
    -0.07
    POSITIVE LOGITS
     festive
    0.08
    especially
    0.07
     Feast
    0.07
     т
    0.07
    ss
    0.07
    ת
    0.07
    истема
    0.07
     Stylish
    0.07
     dunkel
    0.07
    uss
    0.07
    Activations Density 0.000%

    No Known Activations