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. 87967
    Prev
    Next
    INDEX
    Explanations

    management

    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
     leid
    -0.08
    (question
    -0.08
     gefragt
    -0.07
    甚至
    -0.07
     fragen
    -0.07
     použit
    -0.07
     altında
    -0.07
     sogenannte
    -0.07
    knowledge
    -0.07
     م
    -0.07
    POSITIVE LOGITS
     Hampton
    0.09
     Recharge
    0.09
    Recharge
    0.08
    тарына
    0.08
     lente
    0.08
     Documents
    0.08
     ocupar
    0.08
     HV
    0.08
    тарының
    0.08
     শর
    0.07
    Activations Density 0.000%

    No Known Activations