© 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. 11-RESID-POST-AA
    11. 68472
    Prev
    Next
    INDEX
    Explanations

    code and legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    яма
    -0.08
    يلة
    -0.08
     ورته
    -0.08
    ées
    -0.07
     أنهم
    -0.07
    ема
    -0.07
     تعب
    -0.07
    倾
    -0.07
     þau
    -0.07
     prosperous
    -0.07
    POSITIVE LOGITS
     bestehenden
    0.17
     기존
    0.15
     originally
    0.15
     existing
    0.15
     Existing
    0.15
    _existing
    0.15
     existente
    0.14
    Existing
    0.14
     ohnehin
    0.14
     existentes
    0.14
    Activations Density 0.235%

    No Known Activations