© 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. 11-RESID-POST-AA
    11. 91392
    Prev
    Next
    INDEX
    Explanations

    {

    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
     doxy
    -0.08
     希
    -0.08
     THINK
    -0.08
    希望
    -0.07
    ，希望
    -0.07
    納
    -0.07
    олня
    -0.07
    струк
    -0.07
     #{
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    (errno
    0.08
    Terrain
    0.08
    awon
    0.08
    apest
    0.08
     feud
    0.08
    Equip
    0.07
    的问题
    0.07
     Progressive
    0.07
    Cant
    0.07
    iswe
    0.07
    Activations Density 0.000%

    No Known Activations