© 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. 23-RESID-POST-AA
    11. 47762
    Prev
    Next
    INDEX
    Explanations

    Anime/manga

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheap
    -0.09
     murah
    -0.08
     >=
    -0.08
    做代理
    -0.08
     barato
    -0.08
     The
    -0.08
     Let's
    -0.07
     Ø
    -0.07
     HWND
    -0.07
     Locksmith
    -0.07
    POSITIVE LOGITS
     Army
    0.11
    Verse
    0.11
     ऊर्जा
    0.11
     Archives
    0.10
     energy
    0.10
    ’énergie
    0.10
     energies
    0.10
    Arts
    0.10
    能源
    0.09
     Forces
    0.09
    Activations Density 0.027%

    No Known Activations