© 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. 65614
    Prev
    Next
    INDEX
    Explanations

    valid

    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
     sump
    -0.08
     تعالى
    -0.07
    Been
    -0.07
    Hr
    -0.07
     funer
    -0.07
    ative
    -0.07
    രു
    -0.07
     دائم
    -0.07
    洪
    -0.07
    Prere
    -0.07
    POSITIVE LOGITS
     которого
    0.09
    ๆ
    0.08
     Wh
    0.07
     presumably
    0.07
    pli
    0.07
    ')['
    0.07
     serving
    0.07
    {}'.
    0.07
    whose
    0.07
     सहभागी
    0.07
    Activations Density 0.403%

    No Known Activations