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. 76171
    Prev
    Next
    INDEX
    Explanations

    viable

    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
     ध्यान
    -0.08
     बल
    -0.08
     répondre
    -0.07
     же
    -0.07
     स्व
    -0.07
    ργ
    -0.07
     गुर
    -0.07
     YOU
    -0.07
     manufactures
    -0.07
     nehmen
    -0.07
    POSITIVE LOGITS
     tack
    0.08
     strategies
    0.08
    Foundation
    0.08
     Steck
    0.08
     estrategias
    0.08
     candidates
    0.08
    endet
    0.08
    儿
    0.08
     avenues
    0.08
     candidature
    0.07
    Activations Density 0.010%

    No Known Activations