© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 103464
    Prev
    Next
    INDEX
    Explanations

    collaboration

    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
    Not in Any Lists

    No Comments

    Negative Logits
    die
    -0.08
     bizarre
    -0.07
    Embed
    -0.07
    irez
    -0.07
     injectable
    -0.07
     déplacements
    -0.07
    imba
    -0.07
    eben
    -0.07
     Manip
    -0.07
    random
    -0.07
    POSITIVE LOGITS
    合作
    0.16
     партнер
    0.16
     partenaires
    0.16
     agreements
    0.16
     partnerships
    0.15
     consortium
    0.15
     기관
    0.15
     partners
    0.14
     partner
    0.14
     parceiros
    0.14
    Activations Density 0.009%

    No Known Activations