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. 43797
    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
     cursus
    -0.07
    LIK
    -0.07
    felt
    -0.07
     regul
    -0.07
    νό
    -0.07
     masquer
    -0.07
    KF
    -0.07
     Pelle
    -0.07
     bod
    -0.07
     motions
    -0.06
    POSITIVE LOGITS
     Jag
    0.08
     mase
    0.07
     satellite
    0.07
    下面
    0.07
    pra
    0.07
     Mainland
    0.07
    此同时
    0.07
    lassical
    0.07
    リア
    0.07
    sha
    0.07
    Activations Density 0.036%

    No Known Activations