© 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. 23-RESID-POST-AA
    11. 47631
    Prev
    Next
    INDEX
    Explanations

    ac

    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
    တွေ
    -0.08
     gen
    -0.08
     flavor
    -0.08
     tr
    -0.08
     flavorful
    -0.08
    -0.07
    ​ដ
    -0.07
    _der
    -0.07
    Graphics
    -0.07
    bae
    -0.07
    POSITIVE LOGITS
     hydrate
    0.08
    Trusted
    0.08
     overheating
    0.07
    endimento
    0.07
    irp
    0.07
    ocused
    0.07
    atı
    0.07
     Billie
    0.07
     cooldown
    0.07
     melt
    0.07
    Activations Density 0.000%
    No Known Activations