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. 43250
    Prev
    Next
    INDEX
    Explanations

    zi

    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
    خلص
    -0.09
    Splitter
    -0.09
     شكل
    -0.08
     البر
    -0.08
     Pinto
    -0.08
     pec
    -0.08
    ancienne
    -0.08
     commuters
    -0.08
    delingen
    -0.08
    Spl
    -0.08
    POSITIVE LOGITS
     stu
    0.08
    afx
    0.08
     my
    0.08
     preced
    0.08
    ure
    0.07
     vf
    0.07
     неф
    0.07
     chaired
    0.07
     wheat
    0.07
     tense
    0.07
    Activations Density 0.001%

    No Known Activations