© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 112473
    Prev
    Next
    INDEX
    Explanations

    mutually exclusive options

    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
     zemlje
    -0.09
     таш
    -0.08
    onte
    -0.08
     Tokio
    -0.08
    .strftime
    -0.08
     богат
    -0.08
     тава
    -0.07
     дайын
    -0.07
    .street
    -0.07
     provenance
    -0.07
    POSITIVE LOGITS
    เดียว
    0.10
     gegense
    0.10
    Singleton
    0.10
    只能
    0.10
     നിയന്ത്ര
    0.09
     discip
    0.09
    ിപ്പ
    0.09
    _SINGLE
    0.09
     exklus
    0.09
    Normalization
    0.09
    Activations Density 0.003%

    No Known Activations