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. 30569
    Prev
    Next
    INDEX
    Explanations

    Graph relationships

    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
     sma
    -0.09
     shoreline
    -0.08
     తెలుస్త
    -0.08
     banc
    -0.07
     Eus
    -0.07
     democr
    -0.07
     démocr
    -0.07
    observe
    -0.07
     admire
    -0.07
     అభిమాన
    -0.07
    POSITIVE LOGITS
     descriptive
    0.09
    ecil
    0.08
    altung
    0.08
    ประเภท
    0.08
    േള
    0.08
    േദ
    0.08
     ye
    0.07
     വരുന്ന
    0.07
     پیچ
    0.07
     differentiation
    0.07
    Activations Density 0.004%

    No Known Activations