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. 129865
    Prev
    Next
    INDEX
    Explanations

    distinct, different

    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
    jection
    -0.09
    jected
    -0.08
    /')
    -0.08
     doonaa
    -0.08
    '),
    -0.08
    895
    -0.08
    irg
    -0.08
    Injector
    -0.08
    ixa
    -0.07
     கொண்டு
    -0.07
    POSITIVE LOGITS
     Bour
    0.08
     Close
    0.07
     szt
    0.07
     starch
    0.07
     Holl
    0.07
     Cave
    0.07
     ול
    0.07
     Dup
    0.07
    纪录
    0.07
     Pu
    0.07
    Activations Density 0.082%

    No Known Activations