© 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. 97722
    Prev
    Next
    INDEX
    Explanations

    UK property rentals

    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
    加拿大
    -0.11
     Toronto
    -0.11
    Canadian
    -0.09
    Toronto
    -0.09
    ２００
    -0.09
     Canadian
    -0.09
     Trudeau
    -0.09
    ２０
    -0.08
     optimisation
    -0.08
     customised
    -0.08
    POSITIVE LOGITS
     letting
    0.14
     Let
    0.13
     lets
    0.13
     let
    0.12
    Let
    0.12
     council
    0.12
     lett
    0.11
     holiday
    0.11
     holidays
    0.10
     Lets
    0.10
    Activations Density 0.035%

    No Known Activations