© 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. 7-RESID-POST-AA
    11. 917
    Prev
    Next
    INDEX
    Explanations

    X

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     भूम
    -0.09
    [counter
    -0.09
     εργ
    -0.08
     Toast
    -0.08
    nsk
    -0.08
    si
    -0.08
     ottenere
    -0.07
     affid
    -0.07
    offset
    -0.07
     konf
    -0.07
    POSITIVE LOGITS
     Acr
    0.09
     buzzing
    0.08
     kidding
    0.07
     centred
    0.07
     cab
    0.07
    ديدة
    0.07
     اك
    0.07
     chance
    0.07
     buzz
    0.07
     acronym
    0.07
    Activations Density 0.001%

    No Known Activations