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. 60729
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     staggering
    -0.08
    -0.08
     buses
    -0.08
     películas
    -0.07
     Flights
    -0.07
     definition
    -0.07
     unsolicited
    -0.07
     anthology
    -0.07
     Oficial
    -0.07
    享
    -0.07
    POSITIVE LOGITS
     muscles
    0.11
     мышцы
    0.10
    臀
    0.09
     thighs
    0.09
     груд
    0.08
     muscul
    0.08
     travaill
    0.08
     muscle
    0.08
     rumpe
    0.08
    肌
    0.08
    Activations Density 0.006%

    No Known Activations