© 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. 23-RESID-POST-AA
    11. 96938
    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abytes
    -0.08
    Adobe
    -0.08
    едлив
    -0.08
    لو
    -0.08
    _usb
    -0.08
    ése
    -0.08
     nwoke
    -0.07
     Nero
    -0.07
    ämm
    -0.07
     мужчины
    -0.07
    POSITIVE LOGITS
    841
    0.14
    84
    0.11
    540
    0.10
    017
    0.09
     Futures
    0.08
    909
    0.08
     ल्य
    0.08
    .Id
    0.08
     எதிர
    0.07
     결과
    0.07
    Activations Density 0.002%

    No Known Activations