© 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. 11-RESID-POST-AA
    11. 114040
    Prev
    Next
    INDEX
    Explanations

    Unparsed data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     palīdz
    -0.08
     thinks
    -0.07
     השת
    -0.07
     Thy
    -0.07
    -food
    -0.07
     régulièrement
    -0.07
     Foley
    -0.07
    iliated
    -0.07
    >M
    -0.07
     Cullen
    -0.07
    POSITIVE LOGITS
     mirrored
    0.11
     reversed
    0.11
     reversal
    0.10
     giro
    0.09
     reciprocal
    0.09
     opposite
    0.09
    mirror
    0.09
    _rev
    0.09
    Swap
    0.09
     mirror
    0.08
    Activations Density 0.081%

    No Known Activations