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. 77369
    Prev
    Next
    INDEX
    Explanations

    parallelism

    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
     preceded
    -0.09
    APA
    -0.08
    。それ
    -0.08
    ;a
    -0.08
    (sprintf
    -0.08
    130
    -0.07
    athers
    -0.07
    mp
    -0.07
    coe
    -0.07
    ;
    -0.07
    POSITIVE LOGITS
     распредел
    0.09
     맡
    0.09
     spatial
    0.09
     slicing
    0.09
     �
    0.09
     توزيع
    0.09
     partition
    0.09
     Allocation
    0.09
    Allocation
    0.09
     تقس
    0.09
    Activations Density 0.002%

    No Known Activations