© 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. 97747
    Prev
    Next
    INDEX
    Explanations

    say "ar" words

    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
    íbrio
    -0.09
    ophagus
    -0.08
    ysis
    -0.08
    inaa
    -0.08
    elerini
    -0.08
    ième
    -0.08
    īja
    -0.07
    aktions
    -0.07
    ের
    -0.07
    ilver
    -0.07
    POSITIVE LOGITS
    aring
    0.14
    arently
    0.13
    ars
    0.12
    ared
    0.11
    lez
    0.11
    alable
    0.09
    aled
    0.09
    ARED
    0.09
    xd
    0.09
    xe
    0.09
    Activations Density 0.003%

    No Known Activations