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. 112274
    Prev
    Next
    INDEX
    Explanations

    driving directions

    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
     expertise
    -0.07
    Too
    -0.07
    Throws
    -0.07
    .DEBUG
    -0.07
     önemli
    -0.07
     relatable
    -0.07
    Pretty
    -0.07
    888
    -0.07
    omial
    -0.07
     Referential
    -0.07
    POSITIVE LOGITS
     pokrač
    0.10
     menuju
    0.10
    一路
    0.09
     edasi
    0.09
     ensuite
    0.09
     splitter
    0.09
     richting
    0.09
     나온
    0.09
    进入
    0.09
     дальше
    0.09
    Activations Density 0.041%

    No Known Activations