Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 19278
    Prev
    Next
    INDEX
    Explanations

    defined

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     υπ
    -0.07
     unacceptable
    -0.07
     highly
    -0.07
     नम
    -0.07
     forget
    -0.07
    μο
    -0.07
    ploader
    -0.07
    ες
    -0.07
     findings
    -0.07
     unfamiliar
    -0.07
    POSITIVE LOGITS
    且
    0.10
     היט
    0.09
    -definition
    0.08
     Hö
    0.08
     überhaupt
    0.08
    zum
    0.08
    VR
    0.08
     puisque
    0.08
     һәм
    0.08
     ובה
    0.08
    Activations Density 0.022%

    No Known Activations