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. 106112
    Prev
    Next
    INDEX
    Explanations

    Comparisons of size

    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
     kabla
    -0.08
     contributions
    -0.08
     convo
    -0.08
    ═
    -0.08
    ــــ
    -0.08
    टना
    -0.08
     courrier
    -0.07
     TORT
    -0.07
     TAC
    -0.07
     census
    -0.07
    POSITIVE LOGITS
     Discount
    0.08
     Storm
    0.07
     Reactive
    0.07
     Levels
    0.07
     siyang
    0.07
     boost
    0.07
     Subscribe
    0.07
     Props
    0.07
    ระดับ
    0.07
     ಮಟ್ಟ
    0.07
    Activations Density 0.003%

    No Known Activations