© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18211
    Prev
    Next
    INDEX
    Explanations

    summar

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    อื่น
    -0.11
    Andere
    -0.11
     autres
    -0.11
    _OTHER
    -0.11
    OTHER
    -0.10
     drugo
    -0.10
     miiran
    -0.10
    anın
    -0.10
    其他
    -0.10
     andere
    -0.10
    POSITIVE LOGITS
    izing
    0.20
    ization
    0.15
    ized
    0.15
    ised
    0.14
    ising
    0.14
    izes
    0.14
    izations
    0.13
    ulated
    0.12
    ise
    0.12
    ening
    0.12
    Activations Density 0.043%

    No Known Activations