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. 15-RESID-POST-AA
    6. 19390
    Prev
    Next
    INDEX
    Explanations

    uri/uki

    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
     전략
    -0.09
     кварт
    -0.09
     обще
    -0.09
     литера
    -0.08
     срещ
    -0.07
    Introdu
    -0.07
     เรื่อง
    -0.07
     มา
    -0.07
     Bak
    -0.07
     فرصة
    -0.07
    POSITIVE LOGITS
    ::-
    0.09
     delir
    0.09
    alp
    0.08
    疼
    0.08
    呻吟
    0.08
    entina
    0.08
     uterus
    0.08
     Schmerzen
    0.08
     diseng
    0.08
     understandably
    0.08
    Activations Density 0.006%

    No Known Activations