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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12824
    Prev
    Next
    INDEX
    Explanations

    DAO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Richmond
    -0.08
     Welch
    -0.08
    ंतु
    -0.08
    investment
    -0.07
     alright
    -0.07
    이며
    -0.07
     Wies
    -0.07
     Rafael
    -0.07
    undle
    -0.07
     gentleman
    -0.07
    POSITIVE LOGITS
    /PT
    0.09
    输
    0.07
     Mahar
    0.07
     <--
    0.07
     precip
    0.07
    mo
    0.07
     lumps
    0.07
     CP
    0.07
     Bale
    0.06
    entukan
    0.06
    Activations Density 0.000%

    No Known Activations