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. 55937
    Prev
    Next
    INDEX
    Explanations

    brown

    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
    _pause
    -0.08
    -winning
    -0.08
     jeopard
    -0.08
    prost
    -0.07
     характера
    -0.07
    -a
    -0.07
    ї
    -0.07
     прис
    -0.07
    ικ
    -0.07
     agr
    -0.07
    POSITIVE LOGITS
     LH
    0.09
    累计
    0.09
     intl
    0.09
     Belly
    0.08
     cumul
    0.08
    ോധ
    0.08
    Oauth
    0.08
     richesse
    0.08
     eras
    0.08
    _AVAILABLE
    0.08
    Activations Density 0.004%

    No Known Activations