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. 58637
    Prev
    Next
    INDEX
    Explanations

    debugging tools

    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
     Cristiano
    -0.08
     Dubai
    -0.08
     Hamburg
    -0.07
    办
    -0.07
    ponential
    -0.07
    .settings
    -0.07
     empowers
    -0.07
    .obs
    -0.07
     tast
    -0.07
     bara
    -0.07
    POSITIVE LOGITS
     malloc
    0.10
     память
    0.10
     অভিযোগ
    0.09
    Malloc
    0.09
     uintptr
    0.09
    llvm
    0.09
    malloc
    0.09
    Warranty
    0.09
     unsafe
    0.09
    _malloc
    0.09
    Activations Density 0.005%

    No Known Activations