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. 15-RESID-POST-AA
    6. 144
    Prev
    Next
    INDEX
    Explanations

    curly brackets and colons

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lear
    -0.09
     sticking
    -0.08
    返回
    -0.07
     returning
    -0.07
     speichern
    -0.07
     DW
    -0.07
     返回
    -0.07
     sticky
    -0.07
     passiert
    -0.07
    teile
    -0.07
    POSITIVE LOGITS
     driveway
    0.08
    oubles
    0.08
     fraud
    0.08
    cuencia
    0.08
     تبلغ
    0.08
     بدأ
    0.08
     мошен
    0.08
    ématiques
    0.08
     allotted
    0.08
     fraudulent
    0.08
    Activations Density 0.000%

    No Known Activations