Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 56152
    Prev
    Next
    INDEX
    Explanations

    (

    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
    Gallery
    -0.07
     Arb
    -0.07
     gallery
    -0.07
     Gallery
    -0.07
    なし
    -0.07
     ICON
    -0.07
     Lust
    -0.07
     ANA
    -0.07
    รง
    -0.07
     Gir
    -0.07
    POSITIVE LOGITS
    llvm
    0.08
     Fey
    0.08
     FStar
    0.07
     proposons
    0.07
    째
    0.07
    flammatory
    0.07
     výro
    0.07
     abusing
    0.07
     reš
    0.07
    țin
    0.07
    Activations Density 0.122%

    No Known Activations