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. 19427
    Prev
    Next
    INDEX
    Explanations

    Chinese text

    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
     percepción
    -0.09
    এর
    -0.09
    CRIP
    -0.09
     आउ
    -0.08
     операция
    -0.08
     операции
    -0.08
     vó
    -0.08
    )،
    -0.08
     warto
    -0.08
     perceptions
    -0.08
    POSITIVE LOGITS
    -party
    0.09
     lain
    0.09
    ward
    0.09
    -set
    0.09
     
    0.09
    面的
    0.08
    -left
    0.08
    grond
    0.08
    -layer
    0.08
    -right
    0.08
    Activations Density 0.022%

    No Known Activations