Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130969
    Prev
    Next
    INDEX
    Explanations

    general

    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
    erdings
    -0.09
    qqat
    -0.08
    odwi
    -0.07
    emonic
    -0.07
    iculously
    -0.07
     աջ
    -0.06
     chaidh
    -0.06
     тих
    -0.06
     markaana
    -0.06
     tới
    -0.06
    POSITIVE LOGITS
     general
    0.71
    general
    0.65
     generales
    0.63
     allgeme
    0.63
     général
    0.62
     generale
    0.62
     genel
    0.62
     générale
    0.61
    General
    0.61
    _general
    0.60
    Activations Density 1.239%

    No Known Activations