© 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. 23-RESID-POST-AA
    11. 47816
    Prev
    Next
    INDEX
    Explanations

    Berlin

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Diablo
    -0.08
     holistic
    -0.08
    Ks
    -0.07
     Columbus
    -0.07
     onsite
    -0.07
     Ks
    -0.07
    Hol
    -0.07
    otis
    -0.07
     sommet
    -0.07
    क्षित
    -0.07
    POSITIVE LOGITS
     تأتي
    0.08
     сіз
    0.07
     estilo
    0.07
     Bant
    0.07
     মন্তব্য
    0.07
    زية
    0.07
     UIP
    0.07
    �
    0.07
    _mes
    0.07
    واض
    0.07
    Activations Density 0.001%

    No Known Activations