© 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. 5749
    Prev
    Next
    INDEX
    Explanations

    PEP 517/518, code

    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
     RAM
    -0.08
     Rub
    -0.08
    _instr
    -0.08
     Humph
    -0.07
    _pass
    -0.07
    _capacity
    -0.07
     Ru
    -0.07
    ru
    -0.07
    tty
    -0.07
    iv
    -0.07
    POSITIVE LOGITS
     قبر
    0.08
     fiet
    0.08
    boj
    0.08
     rey
    0.08
     minn
    0.08
    -Min
    0.08
     lesqu
    0.08
     الليل
    0.08
    071
    0.08
     sue
    0.08
    Activations Density 0.000%

    No Known Activations