© 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. 99232
    Prev
    Next
    INDEX
    Explanations

    ısı

    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
    fäh
    -0.08
     posibilidades
    -0.08
    lvl
    -0.08
    -minded
    -0.08
    Lvl
    -0.08
    sq
    -0.08
     ಫ
    -0.08
    ೋಗ್ಯ
    -0.07
    fähigkeit
    -0.07
    mins
    -0.07
    POSITIVE LOGITS
     noteworthy
    0.08
     خلاف
    0.08
     COMO
    0.08
     наиболее
    0.08
     difficiles
    0.08
     বির
    0.08
    роб
    0.08
     parts
    0.08
     хто
    0.07
     Olympus
    0.07
    Activations Density 0.027%

    No Known Activations