© 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. 2670
    Prev
    Next
    INDEX
    Explanations

    "__:"

    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
    øk
    -0.08
     antic
    -0.07
    ving
    -0.07
     कल
    -0.07
     العقد
    -0.07
     عقد
    -0.07
     niv
    -0.07
    ALIGN
    -0.07
     treb
    -0.07
    Spaces
    -0.07
    POSITIVE LOGITS
     fos
    0.09
     Firma
    0.08
     tamp
    0.08
     wherein
    0.08
    """↵
    0.08
     diving
    0.08
     Said
    0.08
     oma
    0.08
    министр
    0.08
     Oma
    0.07
    Activations Density 0.011%

    No Known Activations