© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 31365
    Prev
    Next
    INDEX
    Explanations

    Renting out assets

    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
     Où
    -0.08
     purification
    -0.08
     poudre
    -0.07
     Ter
    -0.07
    _patch
    -0.07
     FP
    -0.07
     terrestrial
    -0.07
     uporablja
    -0.07
    IGA
    -0.07
     acus
    -0.07
    POSITIVE LOGITS
     Airbnb
    0.10
     apartment
    0.09
     vacant
    0.08
     idle
    0.08
    闲
    0.08
     Door
    0.08
     unused
    0.08
    Door
    0.08
     deler
    0.08
    idle
    0.08
    Activations Density 0.013%

    No Known Activations