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. 43842
    Prev
    Next
    INDEX
    Explanations

    "you only live once"

    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
     сила
    -0.08
    ."""
    -0.07
    _frame
    -0.07
     scaling
    -0.07
     patterns
    -0.07
     Satur
    -0.07
     renewable
    -0.07
    nergies
    -0.07
    вор
    -0.07
    .coe
    -0.07
    POSITIVE LOGITS
    290
    0.08
     subsection
    0.08
     introduct
    0.07
     tournoi
    0.07
    ২০
    0.07
    征
    0.07
    -opening
    0.07
    所以
    0.07
     extranjero
    0.07
    心得
    0.07
    Activations Density 0.002%

    No Known Activations