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. 112285
    Prev
    Next
    INDEX
    Explanations

    byte

    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
     stip
    -0.08
    서를
    -0.08
     свой
    -0.08
    வற்ற
    -0.07
    າ
    -0.07
     Sto
    -0.07
     Cem
    -0.07
     previa
    -0.07
    서는
    -0.07
     Reid
    -0.07
    POSITIVE LOGITS
     Dup
    0.09
    tring
    0.08
    acters
    0.08
    જો
    0.08
    -opt
    0.07
    즈
    0.07
     طور
    0.07
    arten
    0.07
    -alt
    0.07
    遣
    0.07
    Activations Density 0.004%

    No Known Activations