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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 55444
    Prev
    Next
    INDEX
    Explanations

    on time

    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
    istiche
    -0.08
     advies
    -0.08
    283
    -0.08
     shares
    -0.08
    BLOCK
    -0.07
     scattering
    -0.07
     entsteht
    -0.07
    .blocks
    -0.07
    oak
    -0.07
     BLOCK
    -0.07
    POSITIVE LOGITS
     punctual
    0.18
     своев
    0.15
     zuverlässig
    0.14
     puntual
    0.14
     accuracy
    0.14
     timely
    0.14
     impec
    0.13
     flawlessly
    0.13
    准确
    0.13
     düzgün
    0.13
    Activations Density 0.109%

    No Known Activations