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. 46089
    Prev
    Next
    INDEX
    Explanations

    blink

    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
     ters
    -0.08
     باور
    -0.08
     artik
    -0.07
     beers
    -0.07
     yag
    -0.07
     budu
    -0.07
    uzzy
    -0.07
    uilt
    -0.07
    祥
    -0.07
    bellion
    -0.07
    POSITIVE LOGITS
     Encore
    0.09
     postponed
    0.08
     RATE
    0.08
     discarded
    0.08
     Deutschen
    0.08
    Ctor
    0.08
     tasa
    0.08
     Rate
    0.08
    -rate
    0.07
    rate
    0.07
    Activations Density 0.001%

    No Known Activations