© 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. 11-RESID-POST-AA
    11. 94860
    Prev
    Next
    INDEX
    Explanations

    original quotes

    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
    a
    -0.07
     concernés
    -0.07
    `
    -0.07
    quent
    -0.07
    ó
    -0.07
    iados
    -0.07
     paljon
    -0.07
    Esp
    -0.07
    ual
    -0.07
     पुराने
    -0.07
    POSITIVE LOGITS
     hypothetical
    0.14
     hipot
    0.11
     hypot
    0.11
     custom
    0.11
     customised
    0.10
    	custom
    0.10
    custom
    0.10
    ？？
    0.10
     customized
    0.09
    (custom
    0.09
    Activations Density 0.175%

    No Known Activations