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. 56067
    Prev
    Next
    INDEX
    Explanations

    Dates and citations

    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
     progression
    -0.08
    ial
    -0.08
    IAL
    -0.08
    jl
    -0.08
    anku
    -0.07
     inaug
    -0.07
    ogical
    -0.07
     chopping
    -0.07
     keer
    -0.07
    -0.07
    POSITIVE LOGITS
     bereit
    0.08
     Fi
    0.08
     envolvendo
    0.08
     concerning
    0.08
     Rose
    0.07
    强调
    0.07
     primjer
    0.07
    枪
    0.07
     પોતાના
    0.07
     പഠ
    0.07
    Activations Density 0.015%

    No Known Activations