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. 58679
    Prev
    Next
    INDEX
    Explanations

    to

    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
    -0.08
     mills
    -0.07
     adaptés
    -0.07
    (child
    -0.07
    167
    -0.07
    upal
    -0.07
    aper
    -0.07
     accrued
    -0.07
    дин
    -0.07
    ювання
    -0.07
    POSITIVE LOGITS
    策
    0.09
     കാരണം
    0.07
     stolen
    0.07
     eina
    0.07
     месту
    0.07
    айтесь
    0.07
    لىقى
    0.07
     fuq
    0.07
     لقد
    0.07
     ശേഷം
    0.07
    Activations Density 0.004%

    No Known Activations