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. 53032
    Prev
    Next
    INDEX
    Explanations

    speed

    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
     diskr
    -0.08
     pledge
    -0.07
     EVP
    -0.07
     svr
    -0.07
     beaut
    -0.07
     GEO
    -0.07
     sjen
    -0.07
    Latitude
    -0.07
    vek
    -0.07
     dignity
    -0.07
    POSITIVE LOGITS
    -paced
    0.18
     Rapid
    0.15
     rapid
    0.15
     paced
    0.14
    Rapid
    0.14
     hectic
    0.14
     hızlı
    0.14
     frantic
    0.13
     schneller
    0.13
     schnelle
    0.13
    Activations Density 0.072%

    No Known Activations