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. 12186
    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
    Falls
    -0.08
    Dub
    -0.07
     Dub
    -0.07
     undef
    -0.07
    verlet
    -0.07
    umni
    -0.07
    turned
    -0.07
    -0.07
     apporter
    -0.07
     scandal
    -0.07
    POSITIVE LOGITS
     blessings
    0.08
     haya
    0.08
     fst
    0.07
     lanc
    0.07
    �
    0.07
     bakal
    0.07
     lok
    0.07
     eerder
    0.07
     Regina
    0.07
    oek
    0.07
    Activations Density 0.012%

    No Known Activations