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. 19480
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    :**
    -0.11
     различные
    -0.11
    รายละเอียด
    -0.10
    خی
    -0.09
     detalles
    -0.09
    ೆಗಳು
    -0.09
     verschiedene
    -0.09
     inklud
    -0.08
     στοιχεία
    -0.08
     upplýsingar
    -0.08
    POSITIVE LOGITS
    aconda
    0.07
    0.07
    anch
    0.07
    ilog
    0.07
     een
    0.06
     tegenover
    0.06
    iplier
    0.06
    0.06
    parator
    0.06
     isang
    0.06
    Activations Density 0.019%

    No Known Activations