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. 53036
    Prev
    Next
    INDEX
    Explanations

    open

    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
    naire
    -0.08
     cumpr
    -0.07
     nuggets
    -0.07
    ś
    -0.07
     shortcuts
    -0.07
     driver
    -0.06
    uate
    -0.06
    naires
    -0.06
     levert
    -0.06
    direction
    -0.06
    POSITIVE LOGITS
    -minded
    0.12
     minded
    0.11
     ખુલ
    0.10
    weathermap
    0.09
    -hearted
    0.09
    -open
    0.09
     openly
    0.09
     ouvertes
    0.09
    开放
    0.08
     abiertas
    0.08
    Activations Density 0.025%

    No Known Activations