© 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. 23-RESID-POST-AA
    11. 52258
    Prev
    Next
    INDEX
    Explanations

    кол

    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
    Negative Logits
    콘
    -0.08
    temperature
    -0.08
    수
    -0.08
     enig
    -0.08
    텐츠
    -0.08
    terie
    -0.08
     unwavering
    -0.08
    aterials
    -0.08
     matery
    -0.08
    YG
    -0.08
    POSITIVE LOGITS
    jeno
    0.09
    521
    0.09
    ík
    0.08
     tal
    0.08
    ено
    0.07
     cannon
    0.07
     manufactured
    0.07
     represented
    0.07
    .Generic
    0.07
    enoid
    0.07
    Activations Density 0.001%

    No Known Activations