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. 58655
    Prev
    Next
    INDEX
    Explanations

    speaking

    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
    M
    -0.08
     Laravel
    -0.08
    pendencies
    -0.08
     બનાવ
    -0.08
     Sabb
    -0.08
    ન્ક
    -0.08
     undis
    -0.07
     electronic
    -0.07
     નાખ
    -0.07
     માલ
    -0.07
    POSITIVE LOGITS
    ೆರ
    0.08
    Speech
    0.08
     Interviews
    0.07
    .cp
    0.07
     haircut
    0.07
     Baxter
    0.07
     interviews
    0.07
    三个
    0.07
     Hef
    0.07
    기도
    0.07
    Activations Density 0.005%

    No Known Activations