© 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. 3-RESID-POST-AA
    11. 2794
    Prev
    Next
    INDEX
    Explanations

    biographical information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nehme
    -0.09
     moi
    -0.08
     stitches
    -0.07
    urno
    -0.07
     Père
    -0.07
     prenant
    -0.07
    kennt
    -0.07
    oured
    -0.07
     Hass
    -0.07
     finesse
    -0.07
    POSITIVE LOGITS
     onset
    0.08
     deterioration
    0.07
    /**/*
    0.07
    0.07
    wią
    0.07
     bye
    0.07
     Ghana
    0.07
     �
    0.07
     lys
    0.07
     sjø
    0.07
    Activations Density 0.000%
    No Known Activations