© 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. 1363
    Prev
    Next
    INDEX
    Explanations

    tertiary

    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
     Richard
    -0.08
    ု
    -0.08
    ינו
    -0.07
     repress
    -0.07
     Steen
    -0.07
    šlo
    -0.07
    hel
    -0.07
    Kil
    -0.07
    erman
    -0.07
     داشته
    -0.07
    POSITIVE LOGITS
     tert
    0.09
    增
    0.08
     surprisingly
    0.08
     Dad
    0.07
     joys
    0.07
     fp
    0.07
     educ
    0.07
     binn
    0.07
     Ou
    0.07
    .dr
    0.07
    Activations Density 0.003%

    No Known Activations