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. 78708
    Prev
    Next
    INDEX
    Explanations

    global

    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
     IBase
    -0.07
    IBA
    -0.07
     વખતે
    -0.07
     Noch
    -0.07
     BAS
    -0.07
     yup
    -0.07
     mezelf
    -0.07
     mandatory
    -0.07
     Mayo
    -0.07
     jie
    -0.07
    POSITIVE LOGITS
    Winner
    0.08
     triv
    0.08
     minima
    0.08
    -winning
    0.08
     ced
    0.08
     csal
    0.07
     tempered
    0.07
     Michael
    0.07
    restrial
    0.07
     winner
    0.07
    Activations Density 0.002%

    No Known Activations