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

    Neuronpedia

    APICircuit 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. 7-RESID-POST-AA
    6. 131012
    Prev
    Next
    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    okon
    -0.08
    Rsp
    -0.08
    >().
    -0.08
     ecc
    -0.07
     �
    -0.07
    ibr
    -0.07
     traditionally
    -0.07
    ája
    -0.07
     ಸಾಮ
    -0.07
     rsp
    -0.07
    POSITIVE LOGITS
     beschikbare
    0.09
    来看
    0.08
     moż
    0.08
    特点
    0.08
     glean
    0.08
     ônibus
    0.08
     verurs
    0.08
     disponíveis
    0.08
    증
    0.08
     nền
    0.08
    Activations Density 0.016%

    No Known Activations