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. 7-RESID-POST-AA
    6. 131005
    Prev
    Next
    INDEX
    Explanations

    秒

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.09
    gx
    -0.09
     honey
    -0.07
    cx
    -0.07
     Soy
    -0.07
    HM
    -0.07
     Novi
    -0.07
    UEL
    -0.07
     CEL
    -0.07
    osure
    -0.07
    POSITIVE LOGITS
     twin
    0.08
     slit
    0.07
     nose
    0.07
    0.07
    eles
    0.07
     Lambert
    0.07
    Tooltip
    0.07
    Grand
    0.07
     यात
    0.07
     Hof
    0.07
    Activations Density 0.001%

    No Known Activations