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. 76290
    Prev
    Next
    INDEX
    Explanations

    |

    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
     Kay
    -0.08
     Powell
    -0.08
    buddy
    -0.07
    864
    -0.07
     Michigan
    -0.07
     Malt
    -0.07
     Tau
    -0.07
     malt
    -0.07
    比例
    -0.07
     mens
    -0.07
    POSITIVE LOGITS
     grav
    0.08
     Zhu
    0.07
     Strat
    0.07
    בר
    0.07
     keter
    0.07
     fuera
    0.07
    rola
    0.07
    quam
    0.07
    own
    0.07
     вн
    0.07
    Activations Density 0.035%

    No Known Activations