© 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. 52063
    Prev
    Next
    INDEX
    Explanations

    File

    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
     VALUE
    -0.09
    alue
    -0.08
    əh
    -0.08
    hers
    -0.08
    sterdam
    -0.08
    ALUE
    -0.08
    -return
    -0.07
     Giá
    -0.07
    ůst
    -0.07
    VALUE
    -0.07
    POSITIVE LOGITS
    .Delete
    0.13
    .Exists
    0.13
    Info
    0.13
    Share
    0.11
    .Append
    0.11
    .Open
    0.10
    .Move
    0.10
    Stream
    0.10
     IO
    0.10
    .Write
    0.10
    Activations Density 0.001%

    No Known Activations