© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99323
    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
     who've
    -0.09
    ieza
    -0.08
    'environ
    -0.08
    _AV
    -0.07
     Interested
    -0.07
    _ass
    -0.07
    artikel
    -0.07
    _trait
    -0.07
     હતી
    -0.07
     vidas
    -0.07
    POSITIVE LOGITS
     lone
    0.10
     single
    0.10
    ใหญ่
    0.10
     large
    0.09
     अके
    0.09
     بلند
    0.09
     alone
    0.09
     длин
    0.09
     bigger
    0.09
     einzelne
    0.09
    Activations Density 0.058%

    No Known Activations