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. 42053
    Prev
    Next
    INDEX
    Explanations

    atorial

    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
    spa
    -0.08
    との差
    -0.08
    Editing
    -0.08
     đáp
    -0.08
     Latin
    -0.07
    FO
    -0.07
     nost
    -0.07
    Latin
    -0.07
    Designation
    -0.07
    _funcs
    -0.07
    POSITIVE LOGITS
     interpretação
    0.11
     interpret
    0.10
     interpretation
    0.10
     Interpret
    0.10
     interpretar
    0.10
    interpret
    0.10
     interpreta
    0.10
     intuition
    0.10
     intuit
    0.10
     metaphor
    0.10
    Activations Density 0.029%

    No Known Activations