© 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. 23-RESID-POST-AA
    11. 50757
    Prev
    Next
    INDEX
    Explanations

    Po

    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
     zest
    -0.09
    テーマ
    -0.08
     tema
    -0.08
    pieza
    -0.08
     themes
    -0.08
    angepicker
    -0.08
     Courtesy
    -0.08
     teak
    -0.08
     যুগ
    -0.08
     coords
    -0.08
    POSITIVE LOGITS
    isson
    0.24
    issons
    0.16
    ission
    0.16
    ISSION
    0.13
    issions
    0.12
    omial
    0.11
    iss
    0.11
    (ch
    0.10
    wner
    0.10
     poisson
    0.10
    Activations Density 0.001%

    No Known Activations