© 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 EvalsExportsAPI 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. 49766
    Prev
    Next
    INDEX
    Explanations

    opens

    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
     otev
    -0.18
     openen
    -0.18
     öpp
    -0.18
    打开
    -0.17
     öffnen
    -0.16
     Öff
    -0.16
     ouvre
    -0.16
     open
    -0.16
     ouverture
    -0.16
     membuka
    -0.16
    POSITIVE LOGITS
    -ended
    0.19
     ended
    0.17
    ended
    0.17
    Ended
    0.16
    weathermap
    0.13
    ends
    0.11
    ENDED
    0.11
    -minded
    0.11
     wider
    0.10
    -air
    0.10
    Activations Density 0.022%

    No Known Activations