© 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. 11-RESID-POST-AA
    11. 94749
    Prev
    Next
    INDEX
    Explanations

    Sentence beginnings/endings

    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
     quattro
    -0.08
    thing
    -0.08
     जाए
    -0.08
    ukai
    -0.07
     knocks
    -0.07
    ोन
    -0.07
     verr
    -0.07
    unc
    -0.07
    ixin
    -0.07
     zahlreiche
    -0.07
    POSITIVE LOGITS
    _RW
    0.09
     Yas
    0.08
     backpack
    0.08
     wach
    0.08
     emple
    0.08
     obes
    0.08
     Procedure
    0.07
     مز
    0.07
     Ry
    0.07
    gie
    0.07
    Activations Density 0.581%

    No Known Activations