Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44683
    Prev
    Next
    INDEX
    Explanations

    establishments

    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
     mily
    -0.08
     mixtures
    -0.08
     speeds
    -0.08
     gegen
    -0.08
     fractions
    -0.07
     multipl
    -0.07
     mi
    -0.07
     acceler
    -0.07
     gerne
    -0.07
     posición
    -0.07
    POSITIVE LOGITS
     учреждения
    0.12
     อาคาร
    0.10
     Institutions
    0.10
    院
    0.10
     LOGIN
    0.09
     institutions
    0.09
     prédio
    0.09
     कार्यालय
    0.09
     Gebäude
    0.09
     учреж
    0.09
    Activations Density 0.065%

    No Known Activations