© 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. 52260
    Prev
    Next
    INDEX
    Explanations

    .

    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
    -sec
    -0.09
    -commerce
    -0.09
    -aos
    -0.09
     segundos
    -0.08
     vuel
    -0.08
    _STA
    -0.08
    -enabled
    -0.08
    .seconds
    -0.08
    Ux
    -0.08
     seconds
    -0.08
    POSITIVE LOGITS
    25
    0.08
    antino
    0.07
     frères
    0.07
    ২৫
    0.07
     bish
    0.07
     controlling
    0.07
     q
    0.07
     غذایی
    0.07
     yra
    0.07
     Zür
    0.07
    Activations Density 0.002%

    No Known Activations