© 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 EvalsExportsinterp-engineNEWAPI 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. 110967
    Prev
    Next
    INDEX
    Explanations

    sheer

    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
    .columns
    -0.08
     plumbing
    -0.08
     Plumbing
    -0.08
     provin
    -0.07
     Lookup
    -0.07
    Mappings
    -0.07
     infe
    -0.07
     amenities
    -0.07
    apaa
    -0.07
    manın
    -0.07
    POSITIVE LOGITS
     hymn
    0.10
    好友
    0.09
     φί
    0.09
     wav
    0.08
     filtros
    0.08
     filtro
    0.08
    过滤
    0.08
    _FILTER
    0.08
    咖
    0.08
     veil
    0.08
    Activations Density 0.003%

    No Known Activations