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. 13045
    Prev
    Next
    INDEX
    Explanations

    pip

    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
     bia
    -0.08
     ഭ
    -0.08
     hv
    -0.08
     matter
    -0.08
    Qua
    -0.07
    helo
    -0.07
     ab
    -0.07
     продук
    -0.07
    Quaternion
    -0.07
     حاضر
    -0.07
    POSITIVE LOGITS
     سير
    0.09
     EE
    0.08
     ورو
    0.07
    rage
    0.07
    pel
    0.07
    Pel
    0.07
    imports
    0.07
     liens
    0.07
    dex
    0.07
    PE
    0.07
    Activations Density 0.002%

    No Known Activations