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. 43293
    Prev
    Next
    INDEX
    Explanations

    array/list rotation

    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
     punk
    -0.07
     gebraucht
    -0.07
     pumps
    -0.07
    .Lo
    -0.07
     Pokémon
    -0.07
    olated
    -0.07
    658
    -0.07
    Sides
    -0.07
    Locator
    -0.07
    Expression
    -0.07
    POSITIVE LOGITS
     вещ
    0.09
    ,美
    0.09
     enfrentar
    0.09
     críticos
    0.08
     entrar
    0.08
    FULL
    0.08
    GORITH
    0.08
    迎
    0.08
     выйти
    0.08
     complexities
    0.07
    Activations Density 0.000%

    No Known Activations