Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98113
    Prev
    Next
    INDEX
    Explanations

    type

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ểm
    -0.08
     paligid
    -0.07
    มนตรี
    -0.07
    lọwọ
    -0.07
    ביבה
    -0.06
    มหานคร
    -0.06
    шын
    -0.06
     ọrọ
    -0.06
    monton
    -0.06
    нікаў
    -0.06
    POSITIVE LOGITS
    类型
    0.73
     type
    0.71
     प्रकार
    0.71
     પ્રકાર
    0.69
     tipo
    0.67
     types
    0.66
    タイプ
    0.65
     类型
    0.63
     tipos
    0.62
    type
    0.62
    Activations Density 1.427%

    No Known Activations