© 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. 99399
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Kl
    -0.07
    inki
    -0.07
    reading
    -0.07
    agina
    -0.07
     sentences
    -0.07
    浴
    -0.07
     Flames
    -0.07
     Hooks
    -0.07
    او
    -0.07
     gelesen
    -0.07
    POSITIVE LOGITS
     Myers
    0.08
     tilbake
    0.08
    koper
    0.07
     boring
    0.07
     svenske
    0.07
     quadratic
    0.07
     Delgado
    0.07
     NRF
    0.07
     umum
    0.07
    ius
    0.07
    Activations Density 0.000%

    No Known Activations