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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 56282
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    asem
    -0.08
    ean
    -0.08
    landa
    -0.08
    Nl
    -0.07
    leece
    -0.07
     sari
    -0.07
     shedding
    -0.07
    情况下
    -0.07
     Kup
    -0.07
     broadband
    -0.07
    POSITIVE LOGITS
     Mathematical
    0.10
     mathem
    0.09
     계산
    0.09
     математ
    0.09
     Matem
    0.09
     गण
    0.08
    数学
    0.08
    .Cal
    0.08
     গণ
    0.08
     Bruss
    0.08
    Activations Density 0.068%

    No Known Activations