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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 49595
    Prev
    Next
    INDEX
    Explanations

    ию

    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
     nguồn
    -0.10
    counts
    -0.09
     TString
    -0.09
    endere
    -0.08
    erni
    -0.08
    formations
    -0.08
    heading
    -0.08
    gravity
    -0.08
    ogal
    -0.07
     innen
    -0.07
    POSITIVE LOGITS
    нь
    0.14
    ль
    0.11
    ன்
    0.09
    ня
    0.09
    λίου
    0.09
    லை
    0.09
    આરી
    0.08
    న్
    0.08
    ൺ
    0.08
    ляет
    0.08
    Activations Density 0.000%

    No Known Activations