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. 12838
    Prev
    Next
    INDEX
    Explanations

    bingo

    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
     separation
    -0.08
    away
    -0.07
     peeling
    -0.07
     unwrap
    -0.07
     messing
    -0.07
    Visited
    -0.07
    Oc
    -0.07
     cheek
    -0.07
    ந
    -0.07
     visions
    -0.07
    POSITIVE LOGITS
     lifes
    0.08
     চাল
    0.08
    <Address
    0.08
     �
    0.08
     Strat
    0.08
     Bore
    0.07
     breakthroughs
    0.07
     Dengan
    0.07
     electrón
    0.07
     Eureka
    0.07
    Activations Density 0.002%

    No Known Activations