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. 77427
    Prev
    Next
    INDEX
    Explanations

    grid coordinates

    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
     пола
    -0.08
    Stamp
    -0.08
     negativo
    -0.08
     roommates
    -0.08
    silent
    -0.07
    -muted
    -0.07
     negative
    -0.07
    Consent
    -0.07
     negatif
    -0.07
     الأز
    -0.07
    POSITIVE LOGITS
     numbered
    0.10
     numbering
    0.09
     QE
    0.08
     vendas
    0.08
     વેચ
    0.08
     નં
    0.07
     andar
    0.07
     કોર
    0.07
     lebens
    0.07
     નંબર
    0.07
    Activations Density 0.071%

    No Known Activations