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. 111645
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     terg
    -0.08
     sc
    -0.07
    sc
    -0.07
    :value
    -0.07
     arp
    -0.07
     Petit
    -0.07
     eto
    -0.07
     Eiffel
    -0.07
    ٽي
    -0.07
    (sc
    -0.07
    POSITIVE LOGITS
     Newfoundland
    0.08
     Isles
    0.08
     초기
    0.08
     Cristina
    0.08
     Zh
    0.07
     rhyme
    0.07
    initial
    0.07
     Bratis
    0.07
    aurants
    0.07
    Greeting
    0.07
    Activations Density 0.007%

    No Known Activations