© 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. 15-RESID-POST-AA
    11. 16581
    Prev
    Next
    INDEX
    Explanations

    backslash

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Application
    -0.09
     File
    -0.08
    maq
    -0.08
     The
    -0.08
     Administration
    -0.08
     Administrative
    -0.08
     Being
    -0.08
    ətbi
    -0.08
     Several
    -0.07
    var
    -0.07
    POSITIVE LOGITS
     weich
    0.08
     Szene
    0.08
     clo
    0.08
    τητας
    0.08
     қай
    0.08
     nhưng
    0.08
    жди
    0.08
     لیکن
    0.08
    且
    0.08
     जिसकी
    0.08
    Activations Density 0.066%

    No Known Activations