© 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. 31331
    Prev
    Next
    INDEX
    Explanations

    chamber

    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
     영
    -0.08
    awo
    -0.08
    well
    -0.08
    wr
    -0.07
    verbs
    -0.07
    _ing
    -0.07
    ="">
    -0.07
     nke
    -0.07
     girlfriend
    -0.07
     helpful
    -0.07
    POSITIVE LOGITS
     chamber
    0.09
    Arrangement
    0.09
    োখ
    0.09
     ménage
    0.08
     Musik
    0.08
     comprising
    0.08
     arreg
    0.08
    音乐
    0.08
     musicians
    0.08
     recital
    0.08
    Activations Density 0.007%

    No Known Activations