Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 120142
    Prev
    Next
    INDEX
    Explanations

    Chemical formulas

    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
     Sheets
    -0.10
     grocery
    -0.10
     Lightroom
    -0.09
    washing
    -0.08
    -cookie
    -0.08
     �
    -0.08
     supermarket
    -0.08
     gardener
    -0.08
    Cookie
    -0.08
     Cookie
    -0.08
    POSITIVE LOGITS
     embol
    0.09
    锐
    0.08
    _ping
    0.08
     parked
    0.08
     edgy
    0.08
     propulsion
    0.08
     nanot
    0.08
     নিউ
    0.08
    র্ঘ
    0.08
    öt
    0.08
    Activations Density 0.002%

    No Known Activations