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

    Neuronpedia

    APICircuit 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. 12994
    Prev
    Next
    INDEX
    Explanations

    _many

    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
    psilon
    -0.08
    ulling
    -0.08
    rompt
    -0.07
     dich
    -0.07
    ilibr
    -0.07
    belt
    -0.07
    気
    -0.07
    yum
    -0.07
    ruby
    -0.07
    enumer
    -0.07
    POSITIVE LOGITS
     jah
    0.09
    виж
    0.08
    ದೆ
    0.08
     Greatest
    0.08
     preko
    0.08
     vidare
    0.08
     kreat
    0.08
     bolt
    0.08
     største
    0.08
     крип
    0.08
    Activations Density 0.000%

    No Known Activations