© 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. 44925
    Prev
    Next
    INDEX
    Explanations

    ijn

    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
    援
    -0.10
    止
    -0.09
     upstairs
    -0.09
    �
    -0.09
    Punch
    -0.08
    跑
    -0.08
    套利
    -0.08
     tenis
    -0.08
     sple
    -0.08
    aven
    -0.08
    POSITIVE LOGITS
    txt
    0.08
     ಪ್ರಸ
    0.08
     порядка
    0.07
     ets
    0.07
     drill
    0.07
     сөз
    0.07
     etsa
    0.07
     இர
    0.07
     berarti
    0.07
     kali
    0.07
    Activations Density 0.001%

    No Known Activations