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. 11-RESID-POST-AA
    6. 54019
    Prev
    Next
    INDEX
    Explanations

    actions or agendas

    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
    -door
    -0.07
     náv
    -0.07
    ebab
    -0.07
    LOC
    -0.07
    озна
    -0.07
    َع
    -0.07
    )));↵↵
    -0.07
    äische
    -0.07
    Mc
    -0.07
    $j
    -0.07
    POSITIVE LOGITS
     doeleinden
    0.09
     جهت
    0.08
     لتع
    0.08
     purposes
    0.08
     hyvä
    0.08
     Zwecke
    0.08
     məqs
    0.08
     استفاده
    0.08
     целях
    0.08
     geschickt
    0.08
    Activations Density 0.186%

    No Known Activations