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. 56195
    Prev
    Next
    INDEX
    Explanations

    stamp

    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
    -generator
    -0.08
    -person
    -0.08
    .ease
    -0.08
    -defined
    -0.08
    σα
    -0.07
     человеку
    -0.07
     excellent
    -0.07
    -call
    -0.07
     CAD
    -0.07
    -conf
    -0.07
    POSITIVE LOGITS
    来自
    0.07
     jaringan
    0.07
    你的
    0.07
    (javax
    0.07
     plac
    0.07
    ТИ
    0.07
     doanh
    0.07
     জাত
    0.07
    rut
    0.07
    FRING
    0.07
    Activations Density 0.002%

    No Known Activations