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. 112973
    Prev
    Next
    INDEX
    Explanations

    origins or purpose of something

    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
     Hem
    -0.07
    Vector
    -0.07
    ENG
    -0.07
    Hem
    -0.07
    �
    -0.07
     past
    -0.07
    yr
    -0.07
    irt
    -0.07
    -mod
    -0.07
     aerobic
    -0.06
    POSITIVE LOGITS
     bedoeld
    0.10
     gedacht
    0.10
     gegründet
    0.10
     geschaffen
    0.09
     destinada
    0.09
     להתמודד
    0.09
     potrebe
    0.09
     amacı
    0.09
     ontstaan
    0.09
     удоб
    0.09
    Activations Density 0.073%

    No Known Activations