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. 60967
    Prev
    Next
    INDEX
    Explanations

    Mirrors and perspectives

    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
     eý
    -0.08
     المد
    -0.08
     PDA
    -0.08
     forme
    -0.08
     aikaa
    -0.08
    әте
    -0.08
     consigo
    -0.07
     năm
    -0.07
    ’inté
    -0.07
    opọ
    -0.07
    POSITIVE LOGITS
     thousand
    0.08
    546
    0.07
     ultimately
    0.07
     explained
    0.07
     assumptions
    0.07
     vino
    0.07
     properly
    0.07
    kaart
    0.07
     webinar
    0.07
     Ub
    0.07
    Activations Density 0.001%

    No Known Activations