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. 58478
    Prev
    Next
    INDEX
    Explanations

    bat

    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
     multip
    -0.08
    markers
    -0.07
    interaction
    -0.07
    acht
    -0.07
     predictive
    -0.07
    �
    -0.07
     ರ
    -0.07
    hta
    -0.07
    =v
    -0.07
     insinu
    -0.07
    POSITIVE LOGITS
     hiatus
    0.10
     verstandig
    0.09
     соб
    0.08
     Trilogy
    0.08
     âg
    0.08
     Соб
    0.08
     spiritually
    0.08
     Ener
    0.08
     pausa
    0.08
     pony
    0.08
    Activations Density 0.002%

    No Known Activations