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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 54270
    Prev
    Next
    INDEX
    Explanations

    butt

    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
     involvement
    -0.08
     geopolitical
    -0.08
    属
    -0.07
     felt
    -0.07
     बेर
    -0.07
     액
    -0.07
    将在
    -0.07
     Felt
    -0.07
     adults
    -0.07
     fí
    -0.07
    POSITIVE LOGITS
    INT
    0.08
    chtest
    0.08
    .Speed
    0.08
    UTES
    0.07
    @Spring
    0.07
     aaa
    0.07
     Marg
    0.07
     специальные
    0.07
    YTE
    0.07
     દર
    0.07
    Activations Density 0.002%

    No Known Activations