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. 43659
    Prev
    Next
    INDEX
    Explanations

    uke

    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
     IFR
    -0.09
     orally
    -0.08
     forecast
    -0.08
     ISR
    -0.08
     bacter
    -0.07
     inflated
    -0.07
     forex
    -0.07
     annoncer
    -0.07
    forecast
    -0.07
     multipart
    -0.07
    POSITIVE LOGITS
     kata
    0.09
     Kata
    0.09
     कप
    0.08
    Peer
    0.08
     retali
    0.08
     Magdal
    0.08
     Pepe
    0.08
    姐妹
    0.08
     σκο
    0.07
    Duplicate
    0.07
    Activations Density 0.001%

    No Known Activations