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. 19030
    Prev
    Next
    INDEX
    Explanations

    titles

    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
    asyonu
    -0.08
     Anywhere
    -0.08
    .optional
    -0.08
     spont
    -0.08
     spontan
    -0.08
    范围
    -0.08
     işleri
    -0.07
    /colors
    -0.07
     asters
    -0.07
    asyon
    -0.07
    POSITIVE LOGITS
     president
    0.11
     പ്രസിഡന്റ്
    0.11
     President
    0.11
     പ്രസിഡ
    0.11
     superintendent
    0.11
     സെക്രട്ടറി
    0.10
     Deputy
    0.10
    മന്ത്രി
    0.10
    통령
    0.10
     chairman
    0.10
    Activations Density 0.038%

    No Known Activations