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. 111
    Prev
    Next
    INDEX
    Explanations

    bio

    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
     verlie
    -0.08
    栏
    -0.07
    Forced
    -0.07
     manus
    -0.07
     Sim
    -0.07
     Oficial
    -0.07
     инт
    -0.07
     balcon
    -0.07
     studenti
    -0.07
     Pere
    -0.07
    POSITIVE LOGITS
     sustainably
    0.09
     textiles
    0.09
     consumption
    0.09
     sustainable
    0.08
     biomass
    0.08
     Comedy
    0.08
    料理
    0.08
     ventilation
    0.08
     comedy
    0.08
    剤
    0.08
    Activations Density 0.004%

    No Known Activations