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. 88054
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
     messed
    -0.09
     stubborn
    -0.09
    443
    -0.08
     tocar
    -0.08
     Somehow
    -0.08
    543
    -0.08
     préserver
    -0.08
     dokład
    -0.08
     toss
    -0.08
    邪
    -0.08
    POSITIVE LOGITS
    理念
    0.09
    ®
    0.08
     аналог
    0.08
     bespoke
    0.08
    Certified
    0.08
    Launch
    0.08
    Customized
    0.07
     mindfulness
    0.07
     certified
    0.07
     initiatives
    0.07
    Activations Density 0.024%

    No Known Activations