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. 131004
    Prev
    Next
    INDEX
    Explanations

    Star

    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
     theoretically
    -0.07
     कृषि
    -0.07
    .Trim
    -0.07
    rotechn
    -0.07
     Ivy
    -0.07
    Charts
    -0.07
     brig
    -0.07
    ighters
    -0.07
    &type
    -0.07
    Veter
    -0.07
    POSITIVE LOGITS
     സാമ്പ
    0.08
     míd
    0.07
    樣
    0.07
     altro
    0.07
     ദ
    0.07
     dado
    0.07
     natur
    0.07
     zama
    0.07
     മനുഷ്യ
    0.07
     FB
    0.07
    Activations Density 0.000%

    No Known Activations