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. 53051
    Prev
    Next
    INDEX
    Explanations

    point/points

    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
     спустя
    -0.08
     fondament
    -0.08
     docket
    -0.07
    -responsive
    -0.07
     взрос
    -0.07
     produz
    -0.07
    ען
    -0.07
     mbe
    -0.07
     tém
    -0.07
     intro
    -0.07
    POSITIVE LOGITS
    ('../
    0.09
     Tutorials
    0.08
     hacerlo
    0.08
    ("~/
    0.08
    制造
    0.08
    ("../
    0.08
    ("@
    0.08
    ാമ
    0.08
    hare
    0.07
    وبية
    0.07
    Activations Density 0.001%

    No Known Activations