© 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. 3-RESID-POST-AA
    11. 12848
    Prev
    Next
    INDEX
    Explanations

    十分

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ..........
    -0.07
    'autor
    -0.07
    ину
    -0.07
    Autor
    -0.07
    ENER
    -0.07
     ...
↵
    -0.07
    _ISR
    -0.07
    Yu
    -0.07
    ldr
    -0.07
     nécessaire
    -0.07
    POSITIVE LOGITS
     Amber
    0.08
     hypers
    0.08
    illant
    0.08
     Aman
    0.07
    经理
    0.07
     Zir
    0.07
     curly
    0.07
     amber
    0.07
     AZ
    0.07
     markt
    0.07
    Activations Density 0.000%

    No Known Activations