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. 11808
    Prev
    Next
    INDEX
    Explanations

    上

    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
     Bla
    -0.09
     dito
    -0.08
     Dys
    -0.08
     modus
    -0.08
     mo
    -0.08
     chá
    -0.08
     Keeper
    -0.08
    $res
    -0.07
    �
    -0.07
    love
    -0.07
    POSITIVE LOGITS
    �
    0.09
    代理
    0.08
     pertains
    0.08
     जर
    0.07
     pred
    0.07
     secund
    0.07
    ward
    0.07
     गु
    0.07
     ידי
    0.07
     നിന്ന്
    0.07
    Activations Density 0.007%

    No Known Activations