© 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. 19-RESID-POST-AA
    11. 103450
    Prev
    Next
    INDEX
    Explanations

    :

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -0.11
     a
    -0.10
     in
    -0.09
     (
    -0.08
     an
    -0.08
     or
    -0.08
    -0.08
     and
    -0.08
    2
    -0.08
    's
    -0.07
    POSITIVE LOGITS
    <|message|>
    0.12
     шуданд
    0.12
     мебошанд
    0.12
     мекунанд
    0.11
     мешаванд
    0.11
     карданд
    0.11
    оянд
    0.11
    ющий
    0.11
    ۔۔۔۔
    0.11
     намуда
    0.11
    Activations Density 0.001%

    No Known Activations