© 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. 19-RESID-POST-AA
    11. 19180
    Prev
    Next
    INDEX
    Explanations

    trends

    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
     добров
    -0.08
    obozi
    -0.08
     уничтож
    -0.08
     coopération
    -0.07
     қамтамасыз
    -0.07
    .Basic
    -0.07
     vrijwill
    -0.07
     umož
    -0.07
     bénévol
    -0.07
    ilio
    -0.07
    POSITIVE LOGITS
     trends
    0.37
     tendências
    0.35
     tendances
    0.35
     trendy
    0.35
     Trends
    0.34
     tendencias
    0.34
    趋势
    0.34
     trending
    0.31
     최신
    0.31
     trend
    0.31
    Activations Density 0.112%

    No Known Activations