© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 97344
    Prev
    Next
    INDEX
    Explanations

    /d

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nton
    -0.08
    metros
    -0.08
     municipios
    -0.08
    planation
    -0.08
    :#
    -0.08
    terdam
    -0.08
     Roz
    -0.08
    onter
    -0.08
     الشرقية
    -0.08
    ertu
    -0.08
    POSITIVE LOGITS
    ía
    0.12
    ÍA
    0.11
    ia
    0.10
    ie
    0.10
    IA
    0.09
    ý
    0.09
    L
    0.08
    ియా
    0.08
     beyond
    0.08
    ī
    0.08
    Activations Density 0.001%

    No Known Activations