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. 130994
    Prev
    Next
    INDEX
    Explanations

    malfunction/failure

    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
     રચ
    -0.07
     Impression
    -0.07
     enclosing
    -0.07
     ibn
    -0.07
     верш
    -0.07
     preencher
    -0.07
    ologen
    -0.07
     nautical
    -0.07
    antai
    -0.07
     élev
    -0.07
    POSITIVE LOGITS
     malfunction
    0.32
     faulty
    0.25
     failing
    0.22
     failure
    0.22
    故
    0.21
     неис
    0.21
     dysfunctional
    0.21
     defective
    0.21
     dysfunction
    0.20
     failed
    0.20
    Activations Density 0.073%

    No Known Activations