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. 23-RESID-POST-AA
    6. 98552
    Prev
    Next
    INDEX
    Explanations

    quadr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     send
    -0.09
     gönd
    -0.09
     envio
    -0.08
     scel
    -0.08
     enviados
    -0.08
     salen
    -0.08
    发送
    -0.08
     isaanii
    -0.08
     enviada
    -0.08
     йәш
    -0.08
    POSITIVE LOGITS
    ant
    0.16
     III
    0.14
     II
    0.13
     IV
    0.11
    -II
    0.11
     VII
    0.11
    III
    0.11
    _ant
    0.10
     Ant
    0.10
    Ant
    0.10
    Activations Density 0.001%

    No Known Activations