© 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. 17899
    Prev
    Next
    INDEX
    Explanations

    past-tense suffixes

    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
    Negative Logits
    riting
    -0.08
     the
    -0.08
     кирәк
    -0.08
    haling
    -0.08
    umbling
    -0.08
    ítani
    -0.08
    aniro
    -0.08
    ώντας
    -0.07
    _possible
    -0.07
    ാങ്ങ
    -0.07
    POSITIVE LOGITS
    'ed
    0.24
    ’ed
    0.22
    된
    0.21
     செய்யப்பட்ட
    0.20
    ed
    0.19
    された
    0.19
     edilmiş
    0.19
    -produced
    0.18
    'd
    0.18
     edilen
    0.18
    Activations Density 0.144%

    No Known Activations