© 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. 17999
    Prev
    Next
    INDEX
    Explanations

    freedom

    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
     Organizer
    -0.08
     hấp
    -0.07
     dikke
    -0.07
    揉
    -0.07
    认真
    -0.07
     внимания
    -0.07
     tykk
    -0.07
    র্ক
    -0.07
     интенсив
    -0.07
     içine
    -0.07
    POSITIVE LOGITS
     libertad
    0.45
     liberté
    0.45
     liberdade
    0.44
     vrijheid
    0.43
     freedom
    0.43
    自由
    0.42
     своб
    0.41
     자유
    0.40
     آزادی
    0.40
     Freiheit
    0.39
    Activations Density 0.070%

    No Known Activations