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. 23-RESID-POST-AA
    6. 98135
    Prev
    Next
    INDEX
    Explanations

    ary suffix

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     principalmente
    -0.12
    ्टर
    -0.09
    tration
    -0.09
     ainda
    -0.09
    relser
    -0.09
     এখনও
    -0.08
     still
    -0.08
    TERS
    -0.08
     હજુ
    -0.08
     Still
    -0.08
    POSITIVE LOGITS
    ary
    0.25
    ární
    0.25
    àries
    0.25
    ário
    0.24
    ários
    0.23
    ariamente
    0.23
    ária
    0.23
    ärer
    0.23
    ÁRIO
    0.23
    ario
    0.22
    Activations Density 0.025%

    No Known Activations