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. 53864
    Prev
    Next
    INDEX
    Explanations

    Splitting and dividing

    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
     ਸ
    -0.07
     に
    -0.07
     versatility
    -0.07
     hoodie
    -0.07
    -0.07
     desempeño
    -0.07
     അധിക
    -0.07
     الداخل
    -0.07
     mong
    -0.07
    cpp
    -0.07
    POSITIVE LOGITS
     Eventually
    0.09
     Rats
    0.08
     extermin
    0.08
     incess
    0.08
    Eventually
    0.08
     aż
    0.08
     Computers
    0.08
     fahren
    0.08
    _until
    0.08
    _FETCH
    0.08
    Activations Density 0.001%

    No Known Activations