© 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. 102608
    Prev
    Next
    INDEX
    Explanations

    circle

    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
     legislative
    -0.08
    aciones
    -0.08
     Menü
    -0.07
    106
    -0.07
    gar
    -0.07
    Handling
    -0.07
     dossiers
    -0.07
    gaming
    -0.07
     toal
    -0.07
     सेवन
    -0.07
    POSITIVE LOGITS
     centered
    0.27
     centred
    0.21
    (center
    0.19
    Centered
    0.19
     radius
    0.18
     केन्द्र
    0.18
    (radius
    0.17
     કેન્દ્ર
    0.16
    _center
    0.16
     Radius
    0.16
    Activations Density 0.027%

    No Known Activations