© 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. 96536
    Prev
    Next
    INDEX
    Explanations

    Über

    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
    .Guid
    -0.08
    shell
    -0.08
    elay
    -0.07
    sche
    -0.07
     Raim
    -0.07
     Jetzt
    -0.07
    지
    -0.07
    efte
    -0.07
     Receiving
    -0.07
    symbol
    -0.07
    POSITIVE LOGITS
     хэмжээ
    0.09
    ziehungen
    0.09
    ziehungs
    0.08
     flask
    0.08
     мекунад
    0.08
    IB
    0.08
     mani
    0.08
    ંબ
    0.08
    tre
    0.08
     tre
    0.08
    Activations Density 0.001%

    No Known Activations