© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102744
    Prev
    Next
    INDEX
    Explanations

    prompt

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     άλλα
    -0.11
     অন্যান্য
    -0.10
     ఇతర
    -0.10
     izinto
    -0.10
     sauran
    -0.09
    юцца
    -0.09
     الأشياء
    -0.09
     سایر
    -0.09
     बताते
    -0.09
     अन्य
    -0.09
    POSITIVE LOGITS
     তৈরি
    0.10
     만들
    0.10
     вариант
    0.09
     Variant
    0.09
    _variant
    0.09
     with
    0.09
     variant
    0.08
     Variante
    0.08
    -template
    0.08
     versión
    0.08
    Activations Density 0.003%

    No Known Activations