© 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. 44804
    Prev
    Next
    INDEX
    Explanations

    Economic

    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
    _relationship
    -0.09
    Timestamp
    -0.08
     পৌঁ
    -0.08
    彼
    -0.08
    .GL
    -0.08
    .extensions
    -0.08
     flaming
    -0.08
     पहुँच
    -0.08
     সম্ভব
    -0.08
    507
    -0.08
    POSITIVE LOGITS
     AK
    0.08
     Escol
    0.08
     Kund
    0.08
    (strlen
    0.07
    issor
    0.07
     Amin
    0.07
     Dick
    0.07
    cidos
    0.07
    ın
    0.07
     flexibel
    0.07
    Activations Density 0.001%

    No Known Activations