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. 11-RESID-POST-AA
    6. 94957
    Prev
    Next
    INDEX
    Explanations

    proportion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _http
    -0.08
    -0.07
    -pr
    -0.07
     lạnh
    -0.07
     adop
    -0.07
     PR
    -0.07
    /http
    -0.07
    _sources
    -0.07
     Lad
    -0.07
    -http
    -0.07
    POSITIVE LOGITS
    突出
    0.11
     impecc
    0.10
     exagger
    0.10
     uncanny
    0.10
     musica
    0.09
     illusion
    0.09
     circumference
    0.09
     instinct
    0.09
    ต่าง
    0.09
     infographic
    0.09
    Activations Density 0.005%

    No Known Activations