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. 49074
    Prev
    Next
    INDEX
    Explanations

    file

    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
    �
    -0.08
     rétro
    -0.07
     koris
    -0.07
     :
    -0.06
    (mx
    -0.06
    -0.06
     Ihe
    -0.06
     �
    -0.06
     engaging
    -0.06
     communities
    -0.06
    POSITIVE LOGITS
     બિલ
    0.09
     મુશ્ક
    0.09
    _conversion
    0.08
     Mede
    0.08
    ანდ
    0.08
     abrir
    0.08
     החיים
    0.08
    જા
    0.08
     ખુલ
    0.08
    ындағы
    0.08
    Activations Density 0.001%

    No Known Activations