Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30688
    Prev
    Next
    INDEX
    Explanations

    rocket launch

    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
     equil
    -0.08
     Berkeley
    -0.08
     intime
    -0.07
    閲
    -0.07
    있
    -0.07
     tabb
    -0.07
     prof
    -0.07
    .focus
    -0.07
     Conn
    -0.07
     clipboard
    -0.07
    POSITIVE LOGITS
     rockets
    0.13
     rocket
    0.11
     लॉन्च
    0.10
     gateways
    0.09
     launching
    0.09
     Gateway
    0.09
    gateway
    0.09
     reusable
    0.08
     GPUs
    0.08
     शक्त
    0.08
    Activations Density 0.007%

    No Known Activations