© 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. 65317
    Prev
    Next
    INDEX
    Explanations

    in

    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
    aning
    -0.08
    oj
    -0.08
    ojas
    -0.08
    issance
    -0.08
    Tracer
    -0.07
    undo
    -0.07
    certainty
    -0.07
    tionen
    -0.07
    alo
    -0.07
     identical
    -0.07
    POSITIVE LOGITS
     proverbial
    0.08
     porém
    0.08
     рынка
    0.08
     SAF
    0.08
    shof
    0.07
    ندوق
    0.07
     nostru
    0.07
     af
    0.07
    (()=>
    0.07
    teenth
    0.07
    Activations Density 0.023%

    No Known Activations