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. 74954
    Prev
    Next
    INDEX
    Explanations

    numbers and time

    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
    ombr
    -0.08
     اض
    -0.08
     destinado
    -0.07
     obrigatório
    -0.07
     sovereignty
    -0.07
     autorización
    -0.07
     Lees
    -0.07
     obligatorio
    -0.07
     تصاویر
    -0.07
     ਦਿੱ
    -0.07
    POSITIVE LOGITS
     handful
    0.09
    几十
    0.09
    吧
    0.08
     hundred
    0.08
    few
    0.08
     few
    0.08
     dozens
    0.08
     folks
    0.07
     feels
    0.07
     hundreds
    0.07
    Activations Density 0.090%

    No Known Activations