© 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. 52042
    Prev
    Next
    INDEX
    Explanations

    .jetbrains

    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
    amil
    -0.07
    wij
    -0.07
     nació
    -0.07
    gres
    -0.07
     جار
    -0.07
    _INS
    -0.07
    iders
    -0.07
     Fue
    -0.06
    mey
    -0.06
    ijds
    -0.06
    POSITIVE LOGITS
     führen
    0.09
    기에
    0.08
    .kotlin
    0.08
    laştır
    0.08
     headset
    0.08
    .python
    0.08
    .heading
    0.08
     Österreich
    0.08
    дың
    0.08
     antenna
    0.08
    Activations Density 0.001%

    No Known Activations