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. 18795
    Prev
    Next
    INDEX
    Explanations

    payment

    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
     favorita
    -0.07
    _atomic
    -0.07
     Поч
    -0.07
    cycling
    -0.07
     từng
    -0.07
    ०
    -0.07
     assigning
    -0.07
    nji
    -0.07
    line
    -0.07
     minuto
    -0.07
    POSITIVE LOGITS
     către
    0.10
     sejumlah
    0.09
    给主人
    0.08
    vergoeding
    0.08
     гіст
    0.08
    赔
    0.08
     Aust
    0.08
     компенса
    0.08
     Venet
    0.08
    实
    0.08
    Activations Density 0.012%

    No Known Activations