© 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. 97821
    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
    imen
    -0.08
    emon
    -0.07
    멘
    -0.07
     Osm
    -0.07
     �
    -0.07
     War
    -0.07
     Fred
    -0.07
    -muted
    -0.07
    iewe
    -0.07
     భావ
    -0.07
    POSITIVE LOGITS
    .rstrip
    0.15
    rstrip
    0.12
    .chomp
    0.11
    arto
    0.08
    ＼
    0.08
     nate
    0.08
    НС
    0.08
    łość
    0.08
    _End
    0.08
     Nhà
    0.08
    Activations Density 0.001%

    No Known Activations