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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103568
    Prev
    Next
    INDEX
    Explanations

    Asian villages and streets

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     एवं
    -0.09
     তথা
    -0.09
    /Delete
    -0.08
     및
    -0.08
    /oder
    -0.08
    -C
    -0.08
    /delete
    -0.08
    /User
    -0.08
    /Internal
    -0.08
     সাং
    -0.08
    POSITIVE LOGITS
     밖
    0.12
    ையின்
    0.12
    밖
    0.12
    ையில்
    0.12
    자의
    0.11
    子的
    0.11
    장에서
    0.11
    ിയുടെ
    0.11
    자가
    0.11
    ையை
    0.10
    Activations Density 0.031%

    No Known Activations