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. 55912
    Prev
    Next
    INDEX
    Explanations

    choice

    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
     faithfully
    -0.07
     piti
    -0.07
    izam
    -0.07
     gradient
    -0.07
     holding
    -0.07
    iter
    -0.07
     posting
    -0.07
    erialized
    -0.07
    ూర్త
    -0.06
    iteks
    -0.06
    POSITIVE LOGITS
     선택
    0.18
     выборе
    0.17
     തിരഞ്ഞെട
    0.17
     lựa
    0.17
     nhọrọ
    0.17
     выбора
    0.17
     scegliere
    0.17
     elegir
    0.16
     выбира
    0.16
     ఎంప
    0.16
    Activations Density 0.103%

    No Known Activations