© 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. 12720
    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_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ye
    -0.09
     pace
    -0.08
     gewinnt
    -0.08
    물을
    -0.08
     ಬೆ
    -0.08
     Zhang
    -0.08
     보면
    -0.08
     intérieur
    -0.08
     നേടിയ
    -0.07
     magnet
    -0.07
    POSITIVE LOGITS
    psis
    0.08
     agon
    0.08
    nt
    0.07
     కాల
    0.07
     clr
    0.07
    -library
    0.07
    -dose
    0.07
     ప్రయ
    0.07
    ّه
    0.07
     colegios
    0.07
    Activations Density 0.001%

    No Known Activations